AIDive

Pack de vídeo

El kit del bucle de retro: convierte una sesión fallida de Claude Code en una comprobación

9 min de lectura

TL;DR y veredicto

Cuando Claude Code ignora una regla, el reflejo es una línea más ruidosa en CLAUDE.md. La doc explica por qué eso falla: Claude trata esos archivos como contexto, no como configuración obligatoria, y para bloquear una acción se usa un hook. s4 El bucle de la retro va en sentido contrario: menos líneas, y una comprobación que no se puede ignorar.

En nuestra prueba, una sesión de Claude Code construyó una funcionalidad de notas de crédito en una API de facturación pequeña y entregó un bug de numeración con sus propios tests en verde. Una retro sobre esa sesión, a la que se le dijo qué falló, propuso lo que lo habría evitado. Aprobamos cuatro cambios a mano: un hook de pre-commit, un test, una línea de estándares y un comentario en el origen. Una sesión nueva con la misma petición entregó después los números sin huecos.

El veredicto:

  • Ejecuta una retro después de una sesión que salió mal, antes de vaciarla, o sobre el log de una sesión antigua.
  • No la ejecutes en piloto automático. Solo propone, y nada cambia hasta que eliges un candidato. s2
  • Rastrea cada candidato hasta un momento del transcript, y descarta los que no puedas rastrear.
  • Lleva cada superviviente al soporte adecuado: una comprobación para un fallo mecánico, una línea de estándares para un juicio, un comentario en el origen para un hueco de navegación.
  • Las comprobaciones que añades son código que ahora mantienes. La retro no audita las comprobaciones que propuso el mes pasado. s2

El pack de abajo incluye el checklist, el script del hook y el test de numeración de nuestra prueba.

Síntesis con fuentes

Qué es la retro. Es un skill de la colección de Matt Pocock. Solo se invoca a mano (disable-model-invocation: true), y busca candidatos en siete categorías: Navigation, Automated checks, Coding standards, Global AGENTS.md, Tool economy, No-ops e Information access. s1 Su último paso solo presenta los candidatos, por orden de gravedad. s1 Pasó al plugin de Claude Code en la v1.3.0. s22

Cómo instalarlo. La línea de instalación es claude plugin install mattpocock-skills@claude-plugins-official. s25 Una trampa: un issue informó de que el comando de la retro faltaba al instalar por el marketplace oficial. s24 La entrada del marketplace ahora fija un commit más reciente. s26 En nuestra máquina el marketplace local seguía en el commit antiguo, así que ejecutamos primero la actualización del marketplace, luego la instalación, y después comprobamos el comando en una sesión nueva.

Por qué el log y no el código. Claude Code guarda los transcripts como JSONL en ~/.claude/projects/<project>/<session-id>.jsonl, y claude --resume <transcript-path> reanuda una sesión desde ese archivo. s8 El formato es interno y cambia entre versiones, así que no construyas scripts sobre él. s8 La retención es de 30 días y se configura con cleanupPeriodDays. s8

La retro es ruidosa hasta que la rastreas. La doc dice que descartes cualquier candidato que no puedas rastrear hasta un momento concreto. s2 También advierte de que el modelo tiende a olvidar las dificultades de la mitad de la sesión e inventa consejos genéricos para llenar las categorías. s2 Un issue abierto cuenta 17 ejecuciones de retro en 12 sesiones, 15 de ellas seguidas de un usuario que pedía al agente demostrar que los candidatos eran necesarios, y pide que cero supervivientes cuente como una retro completa. s7

Lleva cada superviviente a su sitio. Un repo sin barrera, es decir, sin hook de pre-commit ni job de CI que ejecute su comando de lint, type check o tests, es en sí mismo un hallazgo. s1 Una violación mecánica recibe una comprobación determinista, punto. s1 Los archivos de guía deben usarse con muchísima moderación, normalmente solo para punteros de navegación a otros archivos. s1 Un desarrollador que mantiene un bucle de lecciones en producción llega a la misma escalera: una regla que retrocede se convierte en un test, una regla de lint o un hook. s6

Mantén CLAUDE.md pequeño. La doc apunta a menos de 200 líneas por archivo CLAUDE.md, porque los archivos más largos consumen más contexto y reducen el cumplimiento. s4 Su prueba para cada línea: ¿quitarla haría que Claude cometiera errores? Si no, córtala. s9 El modo de fallo de la hinchazón, una regla ignorada que recibe una regla más ruidosa y un archivo más largo, lo describe un desarrollador. s10

Cierra el bucle. La doc dice que trates CLAUDE.md como código: revísalo cuando las cosas van mal, poda con regularidad y prueba los cambios observando si el comportamiento de Claude cambia de verdad. s9 /doctor prompt-audit necesita Claude Code v2.1.283 o posterior, informa de los hallazgos con ediciones propuestas y no cambia nada hasta que lo pidas. s4 Se ejecuta a través del skill claude-api incluido, así que no está disponible mientras ese skill esté desactivado. s4 Y un issue abierto describe la retro implementando los cambios aprobados y olvidando después el commit. s23

Lo que vimos en nuestra prueba. La primera retro empezó con "This session was smooth", porque la sesión nunca supo que había fallado. Solo después de reportar el fallo como argumento encontró la causa, un número tomado antes de validar. Los detalles están en las mediciones de abajo.

Código

Cada archivo es el real de nuestra prueba, o el script que usamos para ejecutarla. Edita las rutas para que coincidan con tu repo.

retro-checklist.md es el checklist de la página como archivo: los siete gestos, la pregunta de rastreo palabra por palabra, los cuatro soportes, el recordatorio del commit y la trampa de la ruta de prompt-audit.

retro-checklist.md

# The retro checklist

Run it after a session that went wrong, before you clear it, or later on the old session's log.

## The seven gestures

1. Install: `claude plugin marketplace update claude-plugins-official`, then `claude plugin install mattpocock-skills@claude-plugins-official --scope project`. Open a NEW session, type a slash, check that the retro command is listed.
2. Run your real task in a plain session. Let it finish. Keep the session open.
3. Run the retro in that session, then run it again with what failed written after it, as its argument. The retro reads the session log, and a session that never learned it failed will call itself smooth.
4. Trace every candidate. Type this, word for word:

   > For each candidate, quote the moment of this session's transcript that backs it; drop any candidate you cannot trace to a specific moment.

   Zero survivors is a valid retro. Weaker survivors are a judgement call: you decide.
5. Approve one survivor at a time, each into its carrier (below). One change per turn, read the diff after each.
6. Run the prompt audit WITH a path, apply its edits if any, then commit the files yourself. The retro proposes and edits, it does not commit.
7. Re-run the same task in a fresh session and watch what it reads first and whether the failure happens again.

## The four carriers

| What failed | Carrier | Example from our run |
| --- | --- | --- |
| A mechanical failure | A deterministic check: a pre-commit hook, a test, a lint rule, a CI job | `pre-commit.sh` (typecheck, then tests) and `numbering.test.ts` |
| A judgement call | One line in `CODING_STANDARDS.md`, read by the reviewer | `CODING_STANDARDS.md` |
| A navigation gap | A comment at the source, or one CLAUDE.md pointer if a comment cannot do it | A doc comment above `nextId` |
| Nothing the above can hold | Do not write a rule | Both retros declined a CLAUDE.md line |

## Traps

- Commit reminder: the retro can implement what you approve and then leave the files uncommitted. Stage the approved files and commit them yourself.
- A new hook checks the working tree, not the commit. If the tree still holds the bug, the hook refuses the commit. Fix the code first, then commit.
- A cherry-pick does not run the pre-commit hook.
- Prompt-audit path trap: `/doctor prompt-audit` with no path audited the user-level files under `~/.claude`, not the repo, and said nothing about the new files. Give it the path: `/doctor prompt-audit CODING_STANDARDS.md`.
- The retro has no dry-run mode. Try a proposed check against the repo before you let it block merges.
- Do not wire the retro to a session-end hook. Keep a human on the approval.
- Keep the transcript format out of your scripts: it is internal and changes between versions.

retro-checklist.md on GitHub

pre-commit.sh es el hook que aprobamos. Ejecuta el type check y luego los tests, y bloquea el commit si alguno falla. Guárdalo como .githooks/pre-commit, hazlo ejecutable y ejecuta git config core.hooksPath .githooks.

pre-commit.sh

#!/bin/sh
set -e
pnpm typecheck
pnpm test

pre-commit.sh on GitHub

numbering.test.ts es el test de vitest que aprobamos. Fija una regla: una petición de nota de crédito rechazada no quema ningún número.

numbering.test.ts

import { describe, expect, it } from "vitest";
import { seedCustomer, seedOpenInvoice, testApp } from "./helpers";

describe("credit note numbering", () => {
  it("does not burn a number on a rejected request", async () => {
    const app = testApp();
    const customerId = await seedCustomer(app);
    const id = await seedOpenInvoice(app, { customerId, unitPrice: 10_000 });
    await app.handle("POST", `/invoices/${id}/pay`);
    const url = `/invoices/${id}/credit-notes`;

    const first = await app.handle("POST", url, { amount: 4_000 });
    expect(first.body).toMatchObject({ number: "CN-0001" });

    const rejected = await app.handle("POST", url, { amount: 6_001 });
    expect(rejected.status).not.toBe(201);

    const next = await app.handle("POST", url, { amount: 6_000 });
    expect(next.status).toBe(201);
    expect(next.body).toMatchObject({ number: "CN-0002" });
  });
});

numbering.test.ts on GitHub

CODING_STANDARDS.md es la línea de estándares que aprobamos, el archivo que lee un revisor.

CODING_STANDARDS.md

# Coding standards

- Take a sequence number (`nextId`) only once every validation has passed, so a rejected request leaves the sequence gapless.

CODING_STANDARDS.md on GitHub

retro-output.md es el texto completo de las dos pasadas de retro y las dos respuestas de rastreo de nuestra sesión.

retro-output.md

# Retro output, session A (cb5884fb-bd6f-4684-8866-d0adc12ac26e)

## 1. `/retro` (resumed headless, 2026-10-23 10:39:44, $0.0658, 17.5 s, 5 turns)

Prompt typed: `/retro` -> transcript records `<command-name>/mattpocock-skills:retro</command-name>`. Tool calls: Skill(mattpocock-skills:writing-for-agents), Bash(ls -a; ls .github; ls .git/hooks | grep -v sample; cat tsconfig.json), Bash(find .claude -type f; cat .claude/settings*.json).

Verbatim:

> This session was smooth. The pass came out clean on the first typecheck and test run, and I found no `AGENTS.md`/`CLAUDE.md` or `CODING_STANDARDS.md` to prune. The candidates below are in order of severity.
> 
> **1. No guardrail runs the checks (automated checks)**
> - `package.json` already has `test` and `typecheck`, but nothing runs them: there's no `.github/` workflow and no pre-commit hook.
> - This session only stayed green because I ran both by hand. An agent, or a person, can commit a type error or a failing test.
> - **Fix:** add a CI job running `pnpm typecheck && pnpm test`, plus a pre-commit hook running the same. Neither needs prose.
> 
> **2. The migration rule is the one convention that could be missed (automated checks)**
> - The README says "any change to the stored shape bumps `schemaVersion` and adds a migration".
> - I found it only because I read `README.md` while working out the design. If I'd skipped it, nothing would have failed. Adding a field to `StoreData` without a migration still typechecks.
> - **Fix:** a test that fails when someone changes the stored shape without bumping the version. For example, snapshot the output of `migrate({})` and assert the snapshot's `schemaVersion` equals `CURRENT_SCHEMA_VERSION`. This is a deterministic check, so it should replace the README sentence rather than add to it.
> 
> **3. Adding a counter or store collection touches five places (navigation)**
> - Adding credit notes meant editing `types.ts`, `json-store.ts` (the `empty()` function), `migrations.ts` (the migration, plus the fallback defaults at the bottom of `migrate`), `context.ts`, and a new repo file.
> - The `{ customer: 0, invoice: 0, invoiceNumber: 0 }` literal is duplicated in `json-store.ts` and `migrations.ts`. I had to find both with `grep`.
> - **Fix:** have `migrate` build its defaults from one shared `emptyData()`. That removes a hidden dependency rather than documenting it. A pointer in a steering file would cost context on every turn and go stale, so I wouldn't write one.
> 
> **4. Nothing for the reviewer to enforce (coding standards)**
> - There's no `CODING_STANDARDS.md`. The README's conventions are mostly mechanical: integer cents, domain functions that don't mutate their input, and which error type maps to which status.
> - A reviewer agent would have no judgement-call rules to apply. I wouldn't add any until a real review miss shows one is needed.
> 
> **5. Tool economy and information access: nothing to change**
> - My one failed Bash call (a rejected heredoc) cost a retry, but that was my command and not the tooling.
> - I had everything I needed, since the tests call `createApp().handle` directly with no server or logs to tee.
> 
> I'd start with 1 and 2. They're small, mechanical, and would catch the likeliest future mistake. Want me to add the CI workflow, the pre-commit hook and the schema-version test?

## 2. Trace step (same session, 10:40:33, $0.0322, 17.1 s, 1 turn)

Prompt: "For each candidate, quote the moment of this session's transcript that backs it; drop any candidate you cannot trace to a specific moment."

Verbatim:

> Two of the five candidates have no support in the transcript, and I got a detail wrong in a third. Here is each one against what actually happened.
> 
> **1. No guardrail: kept**
> - The moment is my `ls -a; ls .github 2>/dev/null; ls .git/hooks | grep -v sample` command. The listing shows `.claude .git .gitignore data node_modules package.json … vitest.config.ts`. There is no `.github`, and the hooks `grep` printed nothing.
> - It isn't a mistake I made, since my own `pnpm typecheck` and `pnpm test` run came back clean. It's a repo-state finding: the checks exist as scripts and nothing runs them.
> 
> **2. Migration rule has no check: dropped**
> - I can't point to a moment where I missed or nearly missed a migration. I read `migrations.ts` in my first big `cat`, before I'd seen the README. I would have found the migration step either way, so my claim that I found it only through the README was wrong.
> - "Nothing would have failed if I'd skipped it" is a hypothetical, not something that happened.
> 
> **3. Five places to touch for a new collection: kept, but weaker than I said**
> - The moment is my batch of edits to `types.ts`, `json-store.ts`, `migrations.ts` and `context.ts`. Two of them changed the same literal, `{ customer: 0, invoice: 0, invoiceNumber: 0 }`, which now reads `…, creditNote: 0`. It appears in both `json-store.ts` and the fallback in `migrate`.
> - I said I "had to find both with `grep`". That's wrong. I never ran one, since the `grep` was in the command that was rejected. I already knew both locations from reading the files, and the edits went through without friction.
> - The duplicated literal is real but caused no trouble. I'd rate it low severity.
> 
> **4. No `CODING_STANDARDS.md`: dropped**
> - The only moment is the `git ls-files` output showing the file doesn't exist. No review step happened in this session and no reviewer missed anything.
> - "I wouldn't add any until a real review miss shows one is needed" was my own opinion, not something the session showed.
> 
> **5. Tool economy: dropped as a finding**
> - The moment is my first Bash call being rejected with `Contains brace with quote character (expansion obfuscation)`. It cost one retry, and I switched to Write and Edit.
> - It was a one-off, and I can't tell from the transcript whether the harness or my heredoc-in-Python approach was at fault. I don't think it justifies a change.
> 
> That leaves candidate 1 as the only solid finding and candidate 3 as a minor one. For 1, I can add a CI workflow and a pre-commit hook that both run `pnpm typecheck && pnpm test`.

## 3. Second `/retro`, with the defect reported by the developer (same session, 10:41:10, $0.0491, 23.1 s, 1 turn, no tool call; it skipped the writing-for-agents reload)

Prompt: `/retro Finance tested this build after the session: they sent a credit note that was too big (rejected, fine), and the next valid credit note came out CN-0004 where CN-0002 was due. Rejected requests burn credit-note numbers. Don't fix the code; run the retro on this session with that failure in mind.`

Verbatim:

> I'm skipping the style-guide reload because it's already in this session. The cause is in my own code, and I traced each finding to a specific moment.
> 
> **What happened**
> - In `issueCreditNote` (`src/http/handlers/invoices.ts`) I call `ctx.store.nextId("creditNote")` first and `createCreditNote(...)` second. `nextId` persists the counter immediately, and `createCreditNote` is what throws the 409 for an over-limit amount. So a rejected request still burns a number.
> - I copied the order from the existing `/issue` handler, which I had read. It does `const n = ctx.store.nextId("invoiceNumber"); const issued = issue(current, ...)`, and `issue()` throws if the invoice isn't a draft. So issuing a non-draft invoice probably burns an `INV-` number the same way. I haven't run that, only read it.
> 
> **1. A test that would have caught it: I wrote the scenario and skipped the assertion (automated checks)**
> - The moment is the test I wrote: "rejects bad amounts (400) and amounts above what is left (409)".
>   ```
>   await app.handle("POST", ..., { amount: 8_000 });
>   expect((await app.handle("POST", ..., { amount: 1_001 })).status).toBe(409);
>   expect((await app.handle("POST", ..., { amount: 1_000 })).status).toBe(201);
>   ```
>   That is exactly Finance's sequence: accept, reject, accept. I only checked status codes, never the number on the last note, which comes out as `CN-0003`.
> - The "numbers credit notes sequentially" test only covers two successful requests in a row.
> - **Fix:** add a test that each numbered sequence (`INV-`, `CN-`) stays gapless after rejected requests. Run it over both sequences, which also exposes the `/issue` case.
> - **Rule:** when a test reaches a failure path, assert the state afterwards, not just the status code.
> 
> **2. `nextId` looks pure but isn't (navigation)**
> - In `json-store.ts`, `nextId(kind)` runs `this.update(...)`, so every call writes to the counter and persists it. The `Store` type in `json-store.ts` has only the signature `nextId(kind: keyof Counters): number;`, with no comment about the side effect.
> - Nothing at the call site tells you to allocate only after validation. This is a gotcha no config reveals, so a short doc comment on `nextId` is worth its cost. Something like: "Consumes the number even if the caller then fails; call it only after validation."
> - Keep it as a comment on `nextId`, not a steering-file line. It matters only to someone calling `nextId`, and it can't go stale there.
> 
> **3. The gapless-numbering convention isn't written down (coding standards)**
> - The README's "Conventions" list has cents, immutability, error-to-status mapping, and migrations. It says nothing about invoice or credit-note numbers being gapless, though the request ("numbered `CN-0001`, `CN-0002`...") implies it.
> - This is partly a judgement call: reviewers need to know that numbers are allocated after validation. One README line would do. Finding 1's test is the deterministic check; the README line explains why the test exists.
> 
> **4. Missing CI, from the first retro: still real, but it wouldn't have helped here**
> - My own typecheck and tests passed, so a CI job would also have passed. I'm keeping it as a separate, unrelated finding, not as a cause of this failure.
> 
> **5. My summary stated the rules but didn't test them**
> - I told you "Rules I chose" and flagged the two-update void risk, but never exercised a rejection followed by a success. The summary read as complete when that path was untested. This is a process gap, and finding 1 is the fix.
> 
> I'd start with 1 and 2. I haven't touched the code, as you asked.

## 4. Trace step on the second retro (same session, 10:41:43, $0.0498, 33.4 s, 1 turn)

Prompt: same trace prompt as section 2.

Verbatim:

> I traced each candidate again. Two survive on firm evidence, two survive but with a gap I should state, and one is dropped.
> 
> **1. Test asserts status but not the number: kept, firm**
> - The moment is the test I wrote in `test/credit-notes.test.ts`:
>   ```
>   await app.handle("POST", `/invoices/${id}/credit-notes`, { amount: 8_000 });
>   expect((await app.handle("POST", `/invoices/${id}/credit-notes`, { amount: 1_001 })).status).toBe(409);
>   expect((await app.handle("POST", `/invoices/${id}/credit-notes`, { amount: 1_000 })).status).toBe(201);
>   ```
>   That is accept, reject, accept, with only status codes checked. By my reading of the handler, the last note comes out as `CN-0003`. I derived that and haven't run it.
> - The adjacent test, "numbers credit notes sequentially…", covers two successes in a row and never a rejection.
> - The cause, which I only read and haven't run, is this in the handler I wrote:
>   ```
>   const id = ctx.store.nextId("creditNote");
>   const note = createCreditNote(invoice, existing, amount, …
>   ```
>   That order matches the existing issue handler, which I read:
>   ```
>   const n = ctx.store.nextId("invoiceNumber");
>   const issued = issue(current, `INV-…`, ctx.now());
>   ```
>   and `issue()` throws `ConflictError` for non-drafts. So the `INV-` sequence very likely has the same leak. I haven't run that either.
> 
> **2. `nextId` has no warning about its side effect: kept, firm on the facts**
> - The moment is the `Store` type I read in `json-store.ts`. `update` has a comment ("Apply a change and persist it (when file-backed)."), while `nextId(kind: keyof Counters): number;` has none. Its implementation calls `this.update(...)`, so it persists immediately.
> - The `/issue` call site I copied has no comment either.
> - I can't show that a comment would have changed what I did, because I never weighed the ordering at all. I copied it. The comment is a bet on the next caller, not a proven fix.
> 
> **3. Gapless numbering isn't written in the README: kept, weaker**
> - The moment is the `README.md` output I read before writing the handler. Its Conventions list covers cents, no mutation, error-to-status mapping and `schemaVersion`. It has no line about numbers.
> - So the agent doing the implementation, meaning me, read the conventions and found nothing on this.
> - I overstated one thing last turn. Your request said "numbered `CN-0001`, `CN-0002`...", and I said that implies gapless numbers. That was my inference, not your words. Finance has now confirmed it as a requirement, but nothing in the original request stated it.
> 
> **4. No CI or pre-commit hook: kept, unrelated to this failure**
> - The moment is my `ls -a; ls .github 2>/dev/null; ls .git/hooks | grep -v sample` output, which showed no `.github` and no hooks.
> - It wouldn't have caught this. My own run ended `Tests 42 passed (42)`, and CI would have passed too.
> 
> **5. "My summary stated rules without testing them": dropped**
> - I can quote the summary ("Rules I chose", plus the line about the void being two separate store updates). But it describes my behaviour, not a change to the environment, and finding 1 already covers the underlying gap. Keeping it would count one moment twice.
> 
> The order of importance is 1, 2, then 3. Finding 4 stays on the list but belongs to a separate piece of work. I still haven't changed any code.

retro-output.md on GitHub

doctor-prompt-audit.md es el prompt audit ejecutado sin ruta y luego con ruta. Muestra la trampa de la ruta.

doctor-prompt-audit.md

# `/doctor prompt-audit` (no path) on the ledgerly copy, session 26612b59-9edd-493b-a397-fb54300fa037

# Prompt audit: Claude Code configuration for ledgerly

**Assumptions**
- **Target model:** Claude Sonnet 5.5, the model running this session. A skill that writes prompts for other models (`prompt-master`) is audited for its Claude-facing text only.
- **Scope:** only the Claude Code configuration that loads into this project, as you specified. I proposed no edits to plugin files.
- **Settings and secrets:** I did not read `.claude/settings.json`, `.mcp.json` or `~/.claude.json`.
- **Edits are not applied.** Every edit below touches `~/.claude/`, so it **affects all projects**.
- **Dependency not verified:** I could not verify that `~/.claude` is under git, so I used no `git blame`. No hunk below relies on history.

**Inventory**
- **Project files:** none. The project root has no `CLAUDE.md`, `CLAUDE.local.md`, `AGENTS.md` or `.claude/` instruction files. The ancestors `/path/to/work` and `/private/tmp` have none either.
- **Managed policy:** no managed-policy `CLAUDE.md` exists.
- **User level:**
  - `~/.claude/CLAUDE.md`, which imports `~/.claude/RTK.md`.
  - `~/.claude/rules/context7.md`.
  - 27 skills under `~/.claude/skills/*/SKILL.md`.
  - There are no `commands/`, `agents/` or `output-styles/` folders.
- **Plugins:** `caveman`, `marketing`, `cowork-plugin-management` and `gleam-reels` are installed. I did not audit them in depth, and they have no findings or edits.
- **Coverage gap:** I read `CLAUDE.md`, `RTK.md`, the rule, `context7-mcp`, most of `prompt-master`, the relevant parts of `graphify`, and the top of `agent-reach`. I covered the other skills (Cloudflare, HyperFrames, browser, media) with signal greps and frontmatter only. I did not read their `references/` subfiles.
- **Possible mismatch:** this session's skill list shows none of the `~/.claude/skills/*` entries. These files may not be loading in this project, so the skill findings may not affect it.


## Findings of the first run

The audit without a path found no project instruction files and went on to audit the user-level files under the home folder instead: six proposed edits and four flags, all about files outside this repository, none applied. That part is left out of this copy because it concerns one developer's personal configuration, not the project.

# Second run: `/doctor prompt-audit CODING_STANDARDS.md` (session 9b5f0cd5-1701-498e-8d05-0355c7f1ece6)

## Prompt audit: `CODING_STANDARDS.md`

**Assumptions**
- **Scope:** only `CODING_STANDARDS.md`, which the request names. The inventory found no `CLAUDE.md`, `AGENTS.md`, rule files, skills, commands or subagents in the repo. `.claude/settings.json` exists but I did not read it, per the audit rules.
- **Target model:** Claude Sonnet 5.5, the model running this audit. The file is read by the coding agent, not by application code.
- **Group 4 (request config and architecture):** not applicable. The file is an agent instruction file and has no request-building code.

**Result: the file is clean.** It has one line, so there is nothing to change and the proposed diff is empty.

**Inventory:** `CODING_STANDARDS.md` has one rule at line 3: "Take a sequence number (`nextId`) only once every validation has passed, so a rejected request leaves the sequence gapless."

**Checks**

| Group | Findings |
|---|---|
| 1 Dated prompt text | 0. The rule has no emphasis, hedging, scaffold or step list. It states a reason, so it is context the model can't know, not a prohibition without provenance. |
| 2 Brittle config files | 0. `git blame` puts the line in `adaa593`, the retro commit that followed the credit-note session. It encodes a failure that actually happened, not a one-off stumble. |
| 3 Tool descriptions | Not applicable. |
| 4 Request config and architecture | Not applicable. |

Group 2 also covers stale facts. `nextId` is still defined (`src/store/json-store.ts:11,52`) and the sequence kinds it names still exist. No other instruction file ranks on the same point, so there is no conflict.

**One thing outside the audit:** the rule is violated in the code. `src/http/handlers/invoices.ts:44` calls `ctx.store.nextId("invoiceNumber")` before `issue()` runs. `issue()` throws `ConflictError` for any non-draft invoice (`src/domain/invoice.ts:42-44`). Issuing an already-issued, paid or void invoice therefore consumes an invoice number and leaves a gap. The fix is to validate first, or to pass an allocator into `issue()` the way `createCreditNote` takes `allocate`. I didn't check `customers.ts:8` or `credit-note.ts`.

This is a code bug, not a prompt problem, and the rule is working as intended. Keep it, and consider an enforcing test: `test/numbering.test.ts` may only cover credit notes. I haven't edited anything.

doctor-prompt-audit.md on GitHub

run-session.sh ejecuta un turno de Claude Code headless en una configuración aislada, solo de proyecto, con una lista de permisos. Edita la línea de entorno para poner la tuya.

run-session.sh

#!/usr/bin/env bash
# Usage: run-session.sh <workdir> <out.json> <prompt> [resume-session-id]
# One headless Claude Code turn with an isolated project-only setup and an allow-list.
set -uo pipefail
W="$1"; OUT="$2"; PROMPT="$3"; SID="${4:-}"
source ./env.sh  # your own env: unset CLAUDE* variables, optionally CLAUDE_CODE_DISABLE_AUTO_MEMORY=1
ALLOWED="Read,Edit,Write,MultiEdit,Glob,Grep,Skill,TodoWrite,Task,Agent,Bash(node:*),Bash(npm:*),Bash(pnpm:*),Bash(npx vitest:*),Bash(npx tsc:*),Bash(tsc:*),Bash(git status:*),Bash(git diff:*),Bash(git log:*),Bash(git add:*),Bash(git commit:*),Bash(git checkout -b:*),Bash(ls:*),Bash(cat:*),Bash(mkdir:*),Bash(head:*),Bash(tail:*),Bash(grep:*),Bash(wc:*),Bash(gh:*)"
DIS="AskUserQuestion,EnterPlanMode,ExitPlanMode,EnterWorktree,ExitWorktree,WebFetch,WebSearch"
ARGS=(-p "$PROMPT")
[ -n "$SID" ] && ARGS+=(--resume "$SID")
cd "$W" || exit 1
T0=$(date +%s)
claude "${ARGS[@]}" --model claude-sonnet-5-5 --permission-mode acceptEdits --output-format json \
  --allowedTools "$ALLOWED" --disallowedTools "$DIS" --setting-sources project --strict-mcp-config \
  > "$OUT" 2> "$OUT.stderr" < /dev/null
RC=$?
echo "rc=$RC wall=$(( $(date +%s) - T0 ))s" | tee "$OUT.wall"
python3 -c "import json,sys;d=json.load(open(sys.argv[1]));print({k:d.get(k) for k in ('session_id','total_cost_usd','duration_ms','num_turns','is_error','subtype')})" "$OUT"

run-session.sh on GitHub

oracle.sh ejecuta el test oculto de finanzas, cinco requisitos comprobados desde fuera de la sesión, sobre una copia de trabajo. Apúntalo a tus propios tests ocultos.

oracle.sh

#!/usr/bin/env bash
# Usage: oracle.sh <workdir> <out.json>  -- the hidden finance test for the credit-note task, run from OUTSIDE the work copy.
H=/path/to/hidden-tests
W="$1"; OUT="$2"
cd "$H" && env -u CLAUDECODE WORK="$W" BASE="$(git -C "$W" rev-list --max-parents=0 HEAD | head -1)" TASK=F2 \
  "$H/node_modules/.bin/vitest" run --reporter=json --outputFile="$OUT" > "$OUT.log" 2>&1
python3 - "$OUT" <<'PY'
import json,sys
j=json.load(open(sys.argv[1]))
for tr in j["testResults"]:
    for a in tr["assertionResults"]:
        print(a["status"].upper(), a["title"]); 
        if a["status"]!="passed": print("   ", " ".join(a.get("failureMessages") or [])[:500].replace("\n"," | "))
PY

oracle.sh on GitHub

sessionA-F2.diff es el código de la sesión que entregó el bug, con el arreglo.

sessionA-F2.diff

diff --git a/README.md b/README.md
index 890f13c..ae1e4f9 100644
--- a/README.md
+++ b/README.md
@@ -27,4 +27,8 @@ pnpm typecheck   # tsc --noEmit
 
 ## Invoice lifecycle
 
-`draft` → (`issue`) → `open` → (`pay`) → `paid`; `draft`/`open` → (`void`) → `void`.
+`draft` → (`issue`) → `open` → (`pay`) → `paid`; `draft`/`open`/`paid` → (`void`) → `void`.
+
+Credit notes (`POST`/`GET /invoices/:id/credit-notes`, numbered `CN-0001`, ...) can be issued against
+`open` or `paid` invoices, up to the invoice total minus earlier credit notes. Open invoices' credits
+reduce the outstanding report. Voiding a paid invoice issues a credit note for whatever is left.
diff --git a/src/domain/credit-note.ts b/src/domain/credit-note.ts
new file mode 100644
index 0000000..9a48b40
--- /dev/null
+++ b/src/domain/credit-note.ts
@@ -0,0 +1,43 @@
+import { ConflictError, ValidationError } from "./errors";
+import { computeTotals, type Invoice } from "./invoice";
+import { assertCents, type Cents, type Currency, sum } from "./money";
+
+export type CreditNote = {
+  id: string;
+  /** CN-0001, ... */
+  number: string;
+  invoiceId: string;
+  currency: Currency;
+  /** cents, always positive */
+  amount: Cents;
+  createdAt: string;
+};
+
+export function parseCreditNoteAmount(body: unknown): Cents {
+  if (typeof body !== "object" || body === null) {
+    throw new ValidationError("body must be an object");
+  }
+  return assertCents((body as Record<string, unknown>).amount, "amount", { min: 1 });
+}
+
+/** What is still creditable on an invoice: its total minus the credit notes already issued. */
+export function remainingCredit(invoice: Invoice, notes: CreditNote[]): Cents {
+  return computeTotals(invoice).total - sum(notes.map((n) => n.amount));
+}
+
+export function createCreditNote(
+  invoice: Invoice,
+  existing: CreditNote[],
+  amount: Cents,
+  ids: { id: string; number: string },
+  now: Date,
+): CreditNote {
+  if (invoice.status !== "open" && invoice.status !== "paid") {
+    throw new ConflictError(`invoice ${invoice.id} is ${invoice.status}, only open or paid invoices can be credited`);
+  }
+  const remaining = remainingCredit(invoice, existing);
+  if (amount > remaining) {
+    throw new ConflictError(`credit note of ${amount} exceeds the ${remaining} still creditable on invoice ${invoice.id}`);
+  }
+  return { ...ids, invoiceId: invoice.id, currency: invoice.currency, amount, createdAt: now.toISOString() };
+}
diff --git a/src/domain/invoice.ts b/src/domain/invoice.ts
index 5b69fc9..1a3967b 100644
--- a/src/domain/invoice.ts
+++ b/src/domain/invoice.ts
@@ -52,8 +52,9 @@ export function markPaid(invoice: Invoice, now: Date): Invoice {
   return { ...invoice, status: "paid", paidAt: now.toISOString() };
 }
 
+/** Paid invoices can be voided too, but the caller must credit what is left on them first. */
 export function voidInvoice(invoice: Invoice, now: Date): Invoice {
-  if (invoice.status === "paid" || invoice.status === "void") {
+  if (invoice.status === "void") {
     throw new ConflictError(`invoice ${invoice.id} is ${invoice.status} and cannot be voided`);
   }
   return { ...invoice, status: "void", voidedAt: now.toISOString() };
diff --git a/src/http/context.ts b/src/http/context.ts
index c0a89d3..38d7ffa 100644
--- a/src/http/context.ts
+++ b/src/http/context.ts
@@ -1,5 +1,6 @@
 import type { Store } from "../store/json-store";
 import { customerRepo } from "../store/customer-repo";
+import { creditNoteRepo } from "../store/credit-note-repo";
 import { invoiceRepo } from "../store/invoice-repo";
 
 export type AppContext = {
@@ -7,8 +8,9 @@ export type AppContext = {
   now: () => Date;
   customers: ReturnType<typeof customerRepo>;
   invoices: ReturnType<typeof invoiceRepo>;
+  creditNotes: ReturnType<typeof creditNoteRepo>;
 };
 
 export function createContext(store: Store, now: () => Date = () => new Date()): AppContext {
-  return { store, now, customers: customerRepo(store), invoices: invoiceRepo(store) };
+  return { store, now, customers: customerRepo(store), invoices: invoiceRepo(store), creditNotes: creditNoteRepo(store) };
 }
diff --git a/src/http/handlers/invoices.ts b/src/http/handlers/invoices.ts
index 09959e1..17b3910 100644
--- a/src/http/handlers/invoices.ts
+++ b/src/http/handlers/invoices.ts
@@ -1,3 +1,4 @@
+import { type CreditNote, createCreditNote, parseCreditNoteAmount, remainingCredit } from "../../domain/credit-note";
 import { ValidationError } from "../../domain/errors";
 import { type Invoice, type InvoiceStatus, issue, markPaid, voidInvoice } from "../../domain/invoice";
 import { parseNewInvoice } from "../../domain/validation";
@@ -51,8 +52,33 @@ export function invoiceRoutes(router: Router, ctx: AppContext): void {
     return { status: 200, body: invoiceView(ctx.invoices.save(paid)) };
   });
 
+  /** Voiding a paid invoice credits whatever is left on it, so the books stay balanced. */
   router.on("POST", "/invoices/:id/void", ({ params }) => {
-    const voided = voidInvoice(ctx.invoices.get(params.id), ctx.now());
+    const current = ctx.invoices.get(params.id);
+    const now = ctx.now();
+    const voided = voidInvoice(current, now);
+    if (current.status === "paid") {
+      const left = remainingCredit(current, ctx.creditNotes.listForInvoice(current.id));
+      if (left > 0) issueCreditNote(current, left);
+    }
     return { status: 200, body: invoiceView(ctx.invoices.save(voided)) };
   });
+
+  router.on("POST", "/invoices/:id/credit-notes", ({ params, body }) => {
+    const invoice = ctx.invoices.get(params.id);
+    const amount = parseCreditNoteAmount(body);
+    return { status: 201, body: issueCreditNote(invoice, amount) };
+  });
+
+  router.on("GET", "/invoices/:id/credit-notes", ({ params }) => {
+    const invoice = ctx.invoices.get(params.id);
+    return { status: 200, body: ctx.creditNotes.listForInvoice(invoice.id) };
+  });
+
+  function issueCreditNote(invoice: Invoice, amount: number): CreditNote {
+    const existing = ctx.creditNotes.listForInvoice(invoice.id);
+    const id = ctx.store.nextId("creditNote");
+    const note = createCreditNote(invoice, existing, amount, { id: `cn_${id}`, number: `CN-${String(id).padStart(4, "0")}` }, ctx.now());
+    return ctx.creditNotes.insert(note);
+  }
 }
diff --git a/src/http/handlers/reports.ts b/src/http/handlers/reports.ts
index 19262c9..c84089a 100644
--- a/src/http/handlers/reports.ts
+++ b/src/http/handlers/reports.ts
@@ -1,4 +1,5 @@
-import { computeTotals, isOverdue } from "../../domain/invoice";
+import { remainingCredit } from "../../domain/credit-note";
+import { isOverdue } from "../../domain/invoice";
 import type { Currency } from "../../domain/money";
 import type { AppContext } from "../context";
 import type { Router } from "../router";
@@ -11,8 +12,8 @@ export function reportRoutes(router: Router, ctx: AppContext): void {
     let count = 0;
     let overdue = 0;
     for (const invoice of ctx.invoices.list({ status: "open" })) {
-      const { total } = computeTotals(invoice);
-      totals[invoice.currency] = (totals[invoice.currency] ?? 0) + total;
+      const owed = remainingCredit(invoice, ctx.creditNotes.listForInvoice(invoice.id));
+      totals[invoice.currency] = (totals[invoice.currency] ?? 0) + owed;
       count += 1;
       if (isOverdue(invoice, now)) overdue += 1;
     }
diff --git a/src/store/credit-note-repo.ts b/src/store/credit-note-repo.ts
new file mode 100644
index 0000000..c922142
--- /dev/null
+++ b/src/store/credit-note-repo.ts
@@ -0,0 +1,14 @@
+import type { CreditNote } from "../domain/credit-note";
+import type { Store } from "./json-store";
+
+export function creditNoteRepo(store: Store) {
+  return {
+    listForInvoice(invoiceId: string): CreditNote[] {
+      return store.read().creditNotes.filter((n) => n.invoiceId === invoiceId);
+    },
+    insert(note: CreditNote): CreditNote {
+      store.update((d) => ({ ...d, creditNotes: [...d.creditNotes, note] }));
+      return note;
+    },
+  };
+}
diff --git a/src/store/json-store.ts b/src/store/json-store.ts
index b404c51..99205b7 100644
--- a/src/store/json-store.ts
+++ b/src/store/json-store.ts
@@ -13,9 +13,10 @@ export type Store = {
 function empty(): StoreData {
   return {
     schemaVersion: CURRENT_SCHEMA_VERSION,
-    counters: { customer: 0, invoice: 0, invoiceNumber: 0 },
+    counters: { customer: 0, invoice: 0, invoiceNumber: 0, creditNote: 0 },
     customers: [],
     invoices: [],
+    creditNotes: [],
   };
 }
 
diff --git a/src/store/migrations.ts b/src/store/migrations.ts
index c8b73a9..91d4f99 100644
--- a/src/store/migrations.ts
+++ b/src/store/migrations.ts
@@ -1,6 +1,6 @@
 import type { StoreData } from "./types";
 
-export const CURRENT_SCHEMA_VERSION = 1;
+export const CURRENT_SCHEMA_VERSION = 2;
 
 type RawData = Record<string, unknown> & { schemaVersion?: number };
 type Migration = (data: RawData) => RawData;
@@ -21,9 +21,18 @@ const v0ToV1: Migration = (data) => {
   };
 };
 
+/** v1 -> v2: credit notes (a `creditNotes` list and a `creditNote` counter). */
+const v1ToV2: Migration = (data) => ({
+  ...data,
+  schemaVersion: 2,
+  counters: { creditNote: 0, ...(data.counters as Record<string, number> | undefined) },
+  creditNotes: (data.creditNotes as unknown[] | undefined) ?? [],
+});
+
 /** migrations[n] upgrades a file from version n to n + 1. */
 const migrations: Record<number, Migration> = {
   0: v0ToV1,
+  1: v1ToV2,
 };
 
 export function migrate(raw: unknown): StoreData {
@@ -43,8 +52,9 @@ export function migrate(raw: unknown): StoreData {
   }
   return {
     schemaVersion: CURRENT_SCHEMA_VERSION,
-    counters: (data.counters as StoreData["counters"]) ?? { customer: 0, invoice: 0, invoiceNumber: 0 },
+    counters: (data.counters as StoreData["counters"]) ?? { customer: 0, invoice: 0, invoiceNumber: 0, creditNote: 0 },
     customers: (data.customers as StoreData["customers"]) ?? [],
     invoices: (data.invoices as StoreData["invoices"]) ?? [],
+    creditNotes: (data.creditNotes as StoreData["creditNotes"]) ?? [],
   };
 }
diff --git a/src/store/types.ts b/src/store/types.ts
index 222b191..a9d7277 100644
--- a/src/store/types.ts
+++ b/src/store/types.ts
@@ -1,7 +1,8 @@
+import type { CreditNote } from "../domain/credit-note";
 import type { Customer } from "../domain/customer";
 import type { Invoice } from "../domain/invoice";
 
-export type Counters = { customer: number; invoice: number; invoiceNumber: number };
+export type Counters = { customer: number; invoice: number; invoiceNumber: number; creditNote: number };
 
 /** The shape of the JSON file at CURRENT_SCHEMA_VERSION. */
 export type StoreData = {
@@ -9,4 +10,5 @@ export type StoreData = {
   counters: Counters;
   customers: Customer[];
   invoices: Invoice[];
+  creditNotes: CreditNote[];
 };
diff --git a/test/credit-notes.test.ts b/test/credit-notes.test.ts
new file mode 100644
index 0000000..f841a3c
--- /dev/null
+++ b/test/credit-notes.test.ts
@@ -0,0 +1,94 @@
+import { describe, expect, it } from "vitest";
+import { openStore } from "../src/store/json-store";
+import { migrate } from "../src/store/migrations";
+import { seedCustomer, seedOpenInvoice, testApp } from "./helpers";
+
+async function setup(opts: { unitPrice?: number; discount?: number } = {}) {
+  const app = testApp();
+  const customerId = await seedCustomer(app);
+  const id = await seedOpenInvoice(app, { customerId, unitPrice: opts.unitPrice ?? 10_000, discount: opts.discount });
+  return { app, id };
+}
+
+describe("credit notes", () => {
+  it("numbers credit notes sequentially and lists them per invoice", async () => {
+    const { app, id } = await setup();
+    const first = await app.handle("POST", `/invoices/${id}/credit-notes`, { amount: 2_500 });
+    const second = await app.handle("POST", `/invoices/${id}/credit-notes`, { amount: 1_000 });
+    expect(first.status).toBe(201);
+    expect(first.body).toMatchObject({ number: "CN-0001", invoiceId: id, amount: 2_500, currency: "EUR" });
+    expect(second.body).toMatchObject({ number: "CN-0002" });
+    const list = await app.handle("GET", `/invoices/${id}/credit-notes`);
+    expect((list.body as { number: string }[]).map((n) => n.number)).toEqual(["CN-0001", "CN-0002"]);
+  });
+
+  it("rejects bad amounts (400) and amounts above what is left (409)", async () => {
+    const { app, id } = await setup({ discount: 1_000 });
+    for (const amount of [0, -5, 1.5, "10", undefined]) {
+      expect((await app.handle("POST", `/invoices/${id}/credit-notes`, { amount })).status).toBe(400);
+    }
+    await app.handle("POST", `/invoices/${id}/credit-notes`, { amount: 8_000 });
+    expect((await app.handle("POST", `/invoices/${id}/credit-notes`, { amount: 1_001 })).status).toBe(409);
+    expect((await app.handle("POST", `/invoices/${id}/credit-notes`, { amount: 1_000 })).status).toBe(201);
+  });
+
+  it("refuses drafts and unknown invoices", async () => {
+    const app = testApp();
+    const customerId = await seedCustomer(app);
+    const draft = await app.handle("POST", "/invoices", {
+      customerId,
+      currency: "EUR",
+      lines: [{ description: "x", quantity: 1, unitPrice: 100 }],
+    });
+    const id = (draft.body as { id: string }).id;
+    expect((await app.handle("POST", `/invoices/${id}/credit-notes`, { amount: 10 })).status).toBe(409);
+    expect((await app.handle("GET", "/invoices/inv_999/credit-notes")).status).toBe(404);
+  });
+
+  it("reduces the outstanding report for open invoices", async () => {
+    const { app, id } = await setup();
+    await app.handle("POST", `/invoices/${id}/credit-notes`, { amount: 4_000 });
+    const report = await app.handle("GET", "/reports/outstanding");
+    expect(report.body).toMatchObject({ totals: { EUR: 6_000 }, count: 1 });
+  });
+
+  it("voids a paid invoice by crediting what is left", async () => {
+    const { app, id } = await setup();
+    await app.handle("POST", `/invoices/${id}/pay`);
+    await app.handle("POST", `/invoices/${id}/credit-notes`, { amount: 3_000 });
+    const res = await app.handle("POST", `/invoices/${id}/void`);
+    expect(res.status).toBe(200);
+    expect(res.body).toMatchObject({ status: "void" });
+    const notes = (await app.handle("GET", `/invoices/${id}/credit-notes`)).body as { amount: number }[];
+    expect(notes.map((n) => n.amount)).toEqual([3_000, 7_000]);
+  });
+
+  it("voids a fully credited paid invoice without another note", async () => {
+    const { app, id } = await setup();
+    await app.handle("POST", `/invoices/${id}/pay`);
+    await app.handle("POST", `/invoices/${id}/credit-notes`, { amount: 10_000 });
+    expect((await app.handle("POST", `/invoices/${id}/void`)).status).toBe(200);
+    const notes = (await app.handle("GET", `/invoices/${id}/credit-notes`)).body as unknown[];
+    expect(notes).toHaveLength(1);
+  });
+
+  it("refuses credit notes on void invoices and double voids", async () => {
+    const { app, id } = await setup();
+    await app.handle("POST", `/invoices/${id}/pay`);
+    await app.handle("POST", `/invoices/${id}/void`);
+    expect((await app.handle("POST", `/invoices/${id}/credit-notes`, { amount: 1 })).status).toBe(409);
+    expect((await app.handle("POST", `/invoices/${id}/void`)).status).toBe(409);
+  });
+
+  it("migrates a v1 file by adding the credit note list and counter", () => {
+    const data = migrate({
+      schemaVersion: 1,
+      counters: { customer: 1, invoice: 1, invoiceNumber: 1 },
+      customers: [],
+      invoices: [],
+    });
+    expect(data.creditNotes).toEqual([]);
+    expect(data.counters).toEqual({ customer: 1, invoice: 1, invoiceNumber: 1, creditNote: 0 });
+    expect(openStore().nextId("creditNote")).toBe(1);
+  });
+});
diff --git a/test/invoice.test.ts b/test/invoice.test.ts
index 85202f2..4ad9677 100644
--- a/test/invoice.test.ts
+++ b/test/invoice.test.ts
@@ -53,9 +53,10 @@ describe("invoice domain", () => {
     expect(() => markPaid(draft({ status: "void" }), NOW)).toThrow(ConflictError);
   });
 
-  it("voids drafts and open invoices, never paid ones", () => {
+  it("voids drafts, open and paid invoices, never void ones", () => {
     expect(voidInvoice(draft(), NOW).status).toBe("void");
-    expect(() => voidInvoice(draft({ status: "paid" }), NOW)).toThrow(ConflictError);
+    expect(voidInvoice(draft({ status: "paid" }), NOW).status).toBe("void");
+    expect(() => voidInvoice(draft({ status: "void" }), NOW)).toThrow(ConflictError);
   });
 
   it("knows when an open invoice is overdue", () => {

sessionA-F2.diff on GitHub

sessionB-F2.diff es el código de la sesión nueva que repitió la misma petición.

sessionB-F2.diff

diff --git a/README.md b/README.md
index 890f13c..3aa7a58 100644
--- a/README.md
+++ b/README.md
@@ -28,3 +28,5 @@ pnpm typecheck   # tsc --noEmit
 ## Invoice lifecycle
 
 `draft` → (`issue`) → `open` → (`pay`) → `paid`; `draft`/`open` → (`void`) → `void`.
+A `paid` invoice is voided by crediting whatever is left on it (credit notes `CN-0001`, ..., via
+`POST /invoices/:id/credit-notes` `{ "amount": cents }`; list with `GET`), then it becomes `void`.
diff --git a/src/domain/credit-note.ts b/src/domain/credit-note.ts
new file mode 100644
index 0000000..e2047c3
--- /dev/null
+++ b/src/domain/credit-note.ts
@@ -0,0 +1,39 @@
+import { ConflictError, ValidationError } from "./errors";
+import { computeTotals, type Invoice } from "./invoice";
+import { assertCents, type Cents, type Currency, sum } from "./money";
+
+export type CreditNote = {
+  id: string;
+  /** CN-0001, CN-0002, ... */
+  number: string;
+  invoiceId: string;
+  currency: Currency;
+  /** cents, always > 0 */
+  amount: Cents;
+  createdAt: string;
+};
+
+/** What can still be credited on an invoice: its total minus the credit notes already issued. */
+export function remainingCredit(invoice: Invoice, notes: CreditNote[]): Cents {
+  return computeTotals(invoice).total - sum(notes.map((n) => n.amount));
+}
+
+/** Checks a credit-note request against the invoice and returns the amount. Throws before any number is taken. */
+export function parseCreditAmount(body: unknown, invoice: Invoice, notes: CreditNote[]): Cents {
+  if (typeof body !== "object" || body === null) {
+    throw new ValidationError("body must be an object");
+  }
+  const amount = assertCents((body as Record<string, unknown>).amount, "amount", { min: 1 });
+  if (invoice.status !== "paid") {
+    throw new ConflictError(`invoice ${invoice.id} is ${invoice.status}, only paid invoices can be credited`);
+  }
+  const remaining = remainingCredit(invoice, notes);
+  if (amount > remaining) {
+    throw new ConflictError(`amount ${amount} exceeds the ${remaining} left to credit on invoice ${invoice.id}`);
+  }
+  return amount;
+}
+
+export function creditNumber(n: number): string {
+  return `CN-${String(n).padStart(4, "0")}`;
+}
diff --git a/src/domain/invoice.ts b/src/domain/invoice.ts
index 5b69fc9..60be8ac 100644
--- a/src/domain/invoice.ts
+++ b/src/domain/invoice.ts
@@ -52,8 +52,9 @@ export function markPaid(invoice: Invoice, now: Date): Invoice {
   return { ...invoice, status: "paid", paidAt: now.toISOString() };
 }
 
-export function voidInvoice(invoice: Invoice, now: Date): Invoice {
-  if (invoice.status === "paid" || invoice.status === "void") {
+/** A paid invoice can be voided only once it is fully credited (`fullyCredited`). */
+export function voidInvoice(invoice: Invoice, now: Date, opts: { fullyCredited?: boolean } = {}): Invoice {
+  if ((invoice.status === "paid" && !opts.fullyCredited) || invoice.status === "void") {
     throw new ConflictError(`invoice ${invoice.id} is ${invoice.status} and cannot be voided`);
   }
   return { ...invoice, status: "void", voidedAt: now.toISOString() };
diff --git a/src/http/context.ts b/src/http/context.ts
index c0a89d3..4b26d92 100644
--- a/src/http/context.ts
+++ b/src/http/context.ts
@@ -1,4 +1,5 @@
 import type { Store } from "../store/json-store";
+import { creditNoteRepo } from "../store/credit-note-repo";
 import { customerRepo } from "../store/customer-repo";
 import { invoiceRepo } from "../store/invoice-repo";
 
@@ -7,8 +8,15 @@ export type AppContext = {
   now: () => Date;
   customers: ReturnType<typeof customerRepo>;
   invoices: ReturnType<typeof invoiceRepo>;
+  creditNotes: ReturnType<typeof creditNoteRepo>;
 };
 
 export function createContext(store: Store, now: () => Date = () => new Date()): AppContext {
-  return { store, now, customers: customerRepo(store), invoices: invoiceRepo(store) };
+  return {
+    store,
+    now,
+    customers: customerRepo(store),
+    invoices: invoiceRepo(store),
+    creditNotes: creditNoteRepo(store),
+  };
 }
diff --git a/src/http/handlers/invoices.ts b/src/http/handlers/invoices.ts
index 09959e1..d393c34 100644
--- a/src/http/handlers/invoices.ts
+++ b/src/http/handlers/invoices.ts
@@ -1,3 +1,4 @@
+import { type CreditNote, creditNumber, parseCreditAmount, remainingCredit } from "../../domain/credit-note";
 import { ValidationError } from "../../domain/errors";
 import { type Invoice, type InvoiceStatus, issue, markPaid, voidInvoice } from "../../domain/invoice";
 import { parseNewInvoice } from "../../domain/validation";
@@ -51,8 +52,39 @@ export function invoiceRoutes(router: Router, ctx: AppContext): void {
     return { status: 200, body: invoiceView(ctx.invoices.save(paid)) };
   });
 
+  router.on("POST", "/invoices/:id/credit-notes", ({ params, body }) => {
+    const invoice = ctx.invoices.get(params.id);
+    const amount = parseCreditAmount(body, invoice, ctx.creditNotes.listForInvoice(invoice.id));
+    return { status: 201, body: ctx.creditNotes.insert(newCreditNote(ctx, invoice, amount)) };
+  });
+
+  router.on("GET", "/invoices/:id/credit-notes", ({ params }) => {
+    const invoice = ctx.invoices.get(params.id);
+    return { status: 200, body: ctx.creditNotes.listForInvoice(invoice.id) };
+  });
+
   router.on("POST", "/invoices/:id/void", ({ params }) => {
-    const voided = voidInvoice(ctx.invoices.get(params.id), ctx.now());
+    const current = ctx.invoices.get(params.id);
+    if (current.status !== "paid") {
+      return { status: 200, body: invoiceView(ctx.invoices.save(voidInvoice(current, ctx.now()))) };
+    }
+    // Paid invoice: credit whatever is left, then void it.
+    const left = remainingCredit(current, ctx.creditNotes.listForInvoice(current.id));
+    if (left > 0) ctx.creditNotes.insert(newCreditNote(ctx, current, left));
+    const voided = voidInvoice(current, ctx.now(), { fullyCredited: true });
     return { status: 200, body: invoiceView(ctx.invoices.save(voided)) };
   });
 }
+
+/** Takes the next number: call only once the amount has been validated. */
+function newCreditNote(ctx: AppContext, invoice: Invoice, amount: number): CreditNote {
+  const n = ctx.store.nextId("creditNote");
+  return {
+    id: `cn_${n}`,
+    number: creditNumber(n),
+    invoiceId: invoice.id,
+    currency: invoice.currency,
+    amount,
+    createdAt: ctx.now().toISOString(),
+  };
+}
diff --git a/src/store/credit-note-repo.ts b/src/store/credit-note-repo.ts
new file mode 100644
index 0000000..c922142
--- /dev/null
+++ b/src/store/credit-note-repo.ts
@@ -0,0 +1,14 @@
+import type { CreditNote } from "../domain/credit-note";
+import type { Store } from "./json-store";
+
+export function creditNoteRepo(store: Store) {
+  return {
+    listForInvoice(invoiceId: string): CreditNote[] {
+      return store.read().creditNotes.filter((n) => n.invoiceId === invoiceId);
+    },
+    insert(note: CreditNote): CreditNote {
+      store.update((d) => ({ ...d, creditNotes: [...d.creditNotes, note] }));
+      return note;
+    },
+  };
+}
diff --git a/src/store/json-store.ts b/src/store/json-store.ts
index e1daef5..03df910 100644
--- a/src/store/json-store.ts
+++ b/src/store/json-store.ts
@@ -14,9 +14,10 @@ export type Store = {
 function empty(): StoreData {
   return {
     schemaVersion: CURRENT_SCHEMA_VERSION,
-    counters: { customer: 0, invoice: 0, invoiceNumber: 0 },
+    counters: { customer: 0, invoice: 0, invoiceNumber: 0, creditNote: 0 },
     customers: [],
     invoices: [],
+    creditNotes: [],
   };
 }
 
diff --git a/src/store/migrations.ts b/src/store/migrations.ts
index c8b73a9..e8545db 100644
--- a/src/store/migrations.ts
+++ b/src/store/migrations.ts
@@ -1,6 +1,6 @@
 import type { StoreData } from "./types";
 
-export const CURRENT_SCHEMA_VERSION = 1;
+export const CURRENT_SCHEMA_VERSION = 2;
 
 type RawData = Record<string, unknown> & { schemaVersion?: number };
 type Migration = (data: RawData) => RawData;
@@ -21,9 +21,18 @@ const v0ToV1: Migration = (data) => {
   };
 };
 
+/** v1 -> v2: credit notes (`creditNotes` list and `counters.creditNote`). */
+const v1ToV2: Migration = (data) => ({
+  ...data,
+  schemaVersion: 2,
+  counters: { ...(data.counters as object), creditNote: 0 },
+  creditNotes: [],
+});
+
 /** migrations[n] upgrades a file from version n to n + 1. */
 const migrations: Record<number, Migration> = {
   0: v0ToV1,
+  1: v1ToV2,
 };
 
 export function migrate(raw: unknown): StoreData {
@@ -43,8 +52,9 @@ export function migrate(raw: unknown): StoreData {
   }
   return {
     schemaVersion: CURRENT_SCHEMA_VERSION,
-    counters: (data.counters as StoreData["counters"]) ?? { customer: 0, invoice: 0, invoiceNumber: 0 },
+    counters: (data.counters as StoreData["counters"]) ?? { customer: 0, invoice: 0, invoiceNumber: 0, creditNote: 0 },
     customers: (data.customers as StoreData["customers"]) ?? [],
     invoices: (data.invoices as StoreData["invoices"]) ?? [],
+    creditNotes: (data.creditNotes as StoreData["creditNotes"]) ?? [],
   };
 }
diff --git a/src/store/types.ts b/src/store/types.ts
index 222b191..a9d7277 100644
--- a/src/store/types.ts
+++ b/src/store/types.ts
@@ -1,7 +1,8 @@
+import type { CreditNote } from "../domain/credit-note";
 import type { Customer } from "../domain/customer";
 import type { Invoice } from "../domain/invoice";
 
-export type Counters = { customer: number; invoice: number; invoiceNumber: number };
+export type Counters = { customer: number; invoice: number; invoiceNumber: number; creditNote: number };
 
 /** The shape of the JSON file at CURRENT_SCHEMA_VERSION. */
 export type StoreData = {
@@ -9,4 +10,5 @@ export type StoreData = {
   counters: Counters;
   customers: Customer[];
   invoices: Invoice[];
+  creditNotes: CreditNote[];
 };
diff --git a/test/invoice.test.ts b/test/invoice.test.ts
index 85202f2..97ef4d9 100644
--- a/test/invoice.test.ts
+++ b/test/invoice.test.ts
@@ -53,9 +53,10 @@ describe("invoice domain", () => {
     expect(() => markPaid(draft({ status: "void" }), NOW)).toThrow(ConflictError);
   });
 
-  it("voids drafts and open invoices, never paid ones", () => {
+  it("voids drafts and open invoices, paid ones only when fully credited", () => {
     expect(voidInvoice(draft(), NOW).status).toBe("void");
     expect(() => voidInvoice(draft({ status: "paid" }), NOW)).toThrow(ConflictError);
+    expect(voidInvoice(draft({ status: "paid" }), NOW, { fullyCredited: true }).status).toBe("void");
   });
 
   it("knows when an open invoice is overdue", () => {
diff --git a/test/numbering.test.ts b/test/numbering.test.ts
index a97d189..1fa4dd8 100644
--- a/test/numbering.test.ts
+++ b/test/numbering.test.ts
@@ -20,3 +20,34 @@ describe("credit note numbering", () => {
     expect(next.body).toMatchObject({ number: "CN-0002" });
   });
 });
+
+describe("credit notes and voiding", () => {
+  it("lists credit notes and voids a paid invoice by crediting the rest", async () => {
+    const app = testApp();
+    const customerId = await seedCustomer(app);
+    const id = await seedOpenInvoice(app, { customerId, unitPrice: 10_000 });
+    await app.handle("POST", `/invoices/${id}/pay`);
+    await app.handle("POST", `/invoices/${id}/credit-notes`, { amount: 2_500 });
+
+    const voided = await app.handle("POST", `/invoices/${id}/void`);
+    expect(voided.status).toBe(200);
+    expect(voided.body).toMatchObject({ status: "void" });
+
+    const list = await app.handle("GET", `/invoices/${id}/credit-notes`);
+    expect((list.body as { number: string; amount: number }[]).map((n) => [n.number, n.amount])).toEqual([
+      ["CN-0001", 2_500],
+      ["CN-0002", 7_500],
+    ]);
+  });
+
+  it("rejects bad amounts and unpaid invoices", async () => {
+    const app = testApp();
+    const customerId = await seedCustomer(app);
+    const id = await seedOpenInvoice(app, { customerId });
+    const url = `/invoices/${id}/credit-notes`;
+    expect((await app.handle("POST", url, { amount: 100 })).status).toBe(409);
+    await app.handle("POST", `/invoices/${id}/pay`);
+    expect((await app.handle("POST", url, { amount: 0 })).status).toBe(400);
+    expect((await app.handle("POST", url, {})).status).toBe(400);
+  });
+});
diff --git a/test/store.test.ts b/test/store.test.ts
index a1bf345..82cc59f 100644
--- a/test/store.test.ts
+++ b/test/store.test.ts
@@ -31,7 +31,7 @@ describe("store", () => {
     writeFileSync(
       file,
       JSON.stringify({
-        counters: { customer: 1, invoice: 1, invoiceNumber: 0 },
+        counters: { customer: 1, invoice: 1, invoiceNumber: 0, creditNote: 0 },
         customers: [{ id: "cus_1", name: "Acme", email: "a@acme.io", createdAt: "2025-01-01T00:00:00.000Z" }],
         invoices: [{ id: "inv_1", customer: { id: "cus_1", name: "Acme" }, status: "draft" }],
       }),

sessionB-F2.diff on GitHub

Haz esto el lunes

  • Actualiza el marketplace oficial, instala el pack de skills a nivel de proyecto y comprueba que el comando de la retro aparece en una sesión nueva.
  • Ejecuta tu tarea real en una sesión normal. Deja que termine y mantén la sesión abierta.
  • Ejecuta la retro en esa sesión y luego ejecútala otra vez con el fallo que encontraste escrito detrás.
  • Haz la pregunta de rastreo: "For each candidate, quote the moment of this session's transcript that backs it; drop any candidate you cannot trace to a specific moment."
  • Aprueba los supervivientes de uno en uno en su soporte: una comprobación para un fallo mecánico, una línea de estándares para un juicio, un comentario en el origen para un hueco de navegación.
  • Ejecuta /doctor prompt-audit con la ruta de los archivos que tocaste, aplica sus ediciones y haz el commit de los archivos tú mismo.
  • Repite la misma tarea en una sesión nueva y comprueba que el fallo no ocurre.

Mediciones

Son pruebas pequeñas sobre una API de facturación inventada (Node y TypeScript, TypeScript, vitest) con Claude Code 2.1.294. Son una demostración, no un benchmark. El test oculto de finanzas son cinco comprobaciones escritas antes de la prueba.

Paso Resultado
Tarea de notas de crédito, intento 1 Limpio: 40 pasados, test oculto de finanzas 5/5 (descartado, no es la sesión con el defecto)
Tarea de notas de crédito, intento 2 42 pasados, type check exit 0, test oculto de finanzas 4/5. Salió CN-0004 donde tocaba CN-0002
Primera retro, sin fallo reportado 5 elementos ordenados, empezó con "This session was smooth"
Rastreo de la primera retro 2 supervivientes, 3 descartados
Segunda retro, fallo reportado 5 candidatos
Rastreo de la segunda retro 4 supervivientes, 1 descartado
Aprobado a mano 4 cambios: hook, test, línea de estándares, comentario en el origen. Ninguna línea en CLAUDE.md
Primer intento de commit El hook lo bloqueó: 1 fallido, 42 pasados (43). El árbol aún tenía el código con el bug
Tras el arreglo de una línea Suite 43/43, test oculto de finanzas 5/5, los commits pasaron
Sesión nueva B, misma petición 37 pasados, type check exit 0, test oculto de finanzas 5/5, números sin huecos tras una petición rechazada

Lee estos datos con cuidado:

  • De las dos ejecuciones normales que hicimos con esta tarea, una entregó el bug antes de la retro. Después de la retro tenemos una sola repetición, así que es n=1.
  • La sesión B leyó el archivo de estándares, el hook y el test de numeración en rojo antes de escribir código. Se le entregó la lección. Su acierto muestra el bucle funcionando como se diseñó, no una replicación independiente.
  • La retro nunca encontró el bug por sí sola. Su primera pasada encontró una barrera que faltaba que, en sus propias palabras, no habría atrapado este bug.
  • El nuevo hook comprueba el árbol de trabajo. Un git cherry-pick del commit de la retro sobre la base no lo ejecutó.
  • Sin ruta, el prompt audit leyó los archivos de nivel usuario y no dijo nada de los nuevos. Con la ruta del archivo de estándares respondió que el archivo estaba limpio.
  • La ruta de emisión antigua de ese repo filtra números de factura de la misma manera. La dejamos, queda fuera del alcance de esta sesión.

Para ir más lejos

Lee a quien ejecuta un bucle de lecciones de verdad. Un desarrollador reinyecta un archivo de lecciones con fecha al empezar la sesión y convierte una regla que no deja de fallar en un test, una regla de lint o un hook, con un CLAUDE.md reducido a un router corto. s6

Lee los issues antes de fiarte de la retro. El issue 1173 es el argumento a favor del paso de rastreo. s7 El issue 1311 es el commit olvidado. s23 El issue 1158 es el comando que falta en el marketplace oficial. s24

Aprende dónde viven los logs y cuánto duran. La página de sesiones cubre la ruta de los transcripts, reanudar por ruta y la limpieza a los 30 días. s8

El auto memory es la alternativa automática. Lo dejamos fuera. La queja de un autor sostiene que escribe en silencio, no tiene versiones y guarda trivialidades junto a reglas duraderas, por lo que mantenemos a una persona aprobando cada línea. s11 Tómalo como una opinión y pruébalo en tu propia configuración.

/insights es el compañero semanal. Genera un informe HTML sobre hasta 200 sesiones con puntos de fricción y sugerencias. s14 Un informe de campo convirtió 64 sesiones en 5 líneas de CLAUDE.md, 2 skills y hooks. s12 Aquí no lo ejecutamos.

El bucle de Anthropic es manual. Su artículo sobre el harness describe un ajuste leyendo los logs del evaluador, encontrando dónde divergía su juicio y actualizando el prompt. s13 No encontramos ningún comando oficial de retro ni ningún artículo en la primera página del índice de ingeniería. s27

Por qué no lo automatizamos. Un disparador al final de la sesión sería pegamento escrito por nosotros y sin probar. Los hooks de fin de sesión no pueden bloquear la terminación y tienen un timeout por defecto de 1,5 segundos, y el skill de la retro solo se invoca a mano. s5 s1 La propia doc de la retro dice que solo propone y que nada cambia hasta que eliges un candidato. s2 Mantuvimos a la persona en el bucle.

Lo que dejamos fuera del alcance. El mismo bug de orden existe en la ruta antigua de emisión de facturas de ese repo, y una retro sobre ella sería una prueba aparte. Tampoco añadimos un job de CI, porque nuestra copia no tenía remote y un workflow nunca se habría ejecutado.

FAQ

¿Por qué la retro dijo que mi sesión fue smooth? Lee el log de sesión, y la sesión nunca supo que había fallado: sus tests y su type check estaban en verde. Ejecútala otra vez con lo que falló escrito después del comando, como argumento.

¿La retro cambia mis archivos? Solo propone. Nada cambia hasta que eliges un candidato. s2 Una vez que apruebas, los cambios pueden implementarse pero no commitearse, así que haz el commit tú mismo. s23

¿Puedo ejecutarla sobre una sesión que ya vacié? Sí, si el log sigue en disco. Los transcripts viven en ~/.claude/projects/ y se limpian a los 30 días por defecto, y claude --resume <transcript-path> abre uno. s8

¿Por qué mi hook nuevo bloqueó el commit? Ejecuta tu type check y tus tests sobre el árbol de trabajo. Si el árbol aún tiene el bug que el test ahora atrapa, el commit se rechaza. Arregla primero el código y luego haz el commit.

¿Por qué ninguna línea en CLAUDE.md? Las dos pasadas de nuestra retro rechazaron una, diciendo que un puntero costaría contexto en cada turno y se quedaría obsoleto. La doc apunta a menos de 200 líneas y dice que CLAUDE.md es contexto, no configuración obligatoria. s4

Archivos