Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/doncheli/don-cheli-sddWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/doncheli/don-cheli-sdd/cerrar-sesion)<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/cerrar-sesion"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/cerrar-sesion/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/cerrar-sesion"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/cerrar-sesion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00021 | $0.00670 |
| Opus 5 | $0.00010 | $0.00335 |
| Sonnet 5 | $0.00004 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
cerrar-sesion scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dc:cerrar-sesion
Objetivo
Ritual de fin de sesión que audita cambios, ejecuta checks de calidad, captura aprendizajes y produce un resumen para la próxima sesión. Evita el anti-patrón de cerrar el editor sin guardar contexto.
Adaptado de
wrap-upde Pro-Workflow (rohitg00/pro-workflow).
Uso
/dc:cerrar-sesion
Checklist (obligatorio — no saltar pasos)
1. 📋 Auditoría de Cambios
- ¿Qué archivos se modificaron?
- ¿Hay cambios sin commit?
- ¿Quedaron TODOs en el código?
- ¿Hay archivos temporales que limpiar?
2. ✅ Check de Calidad
- Ejecutar lint
- Ejecutar typecheck
- Ejecutar tests
- ¿Todo pasa? ¿Hay warnings?
3. 🧠 Captura de Aprendizajes
- ¿Qué errores se cometieron?
- ¿Qué patrones funcionaron bien?
- Formatear como:
[APRENDER] Categoría: Regla
4. 🔮 Contexto para Próxima Sesión
- ¿Cuál es la siguiente tarea lógica?
- ¿Hay bloqueantes?
- ¿Qué contexto preservar?
5. 📝 Resumen
- Un párrafo: qué se logró, estado actual, qué sigue
Output
# Cierre de Sesión — 2026-03-21 16:45
## Auditoría
- Archivos modificados: 8
- Commits: 3
- Sin commit: 2 archivos (src/auth.ts, tests/auth.test.ts)
- TODOs encontrados: 1 (src/auth.ts:45 — "TODO: handle refresh token")
## Calidad
- Lint: ✅ sin errors | ⚠️ 2 warnings
- TypeCheck: ✅ pasa
- Tests: ✅ 47/47
- Coverage: 87%
## Aprendizajes
- [APRENDER] Testing: Siempre mockear el servicio de email en tests de auth
- [APRENDER] Git: Hacer commits más pequeños — 3 archivos max
## Próxima Sesión
- Tarea: Implementar refresh token (TODO en auth.ts:45)
- Bloqueante: Ninguno
- Contexto: Branch feature/oauth, PR #23 abierto
## Resumen
Se completó el login con Google OAuth: 3 endpoints nuevos, 12 tests,
integración con NextAuth v5. Falta el refresh token (TODO en auth.ts:45).
PR #23 listo para review excepto por el refresh token.
---
🛑 ¿Cambios sin commit? Stash o commit antes de cerrar.
✅ ¿Listo para cerrar sesión?
Si Tests Fallan
⚠️ NO cerrar sesión con tests fallando. Opciones:
- Corregir antes de cerrar
- Documentar el fallo en el handoff
- Crear issue para el próximo que lo agarre
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 89 lines · 21 tokens per session scan A d8a9f62c53c2
cerrar-sesion is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 670 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
add-todo
Capture idea or task as todo from current conversation context.
forensics
Post-mortem investigation for failed or stuck workflows. Analyzes git history and planning artifacts.
audit-fix
Run audit, prioritize findings, auto-fix via quick tasks, test, and commit.
debug
Systematic debugging with hypothesis testing. Persistent across sessions.
note
Zero-friction idea capture. Append, list, or promote notes to todos.
resume
Pick up where you left off. Restores context and suggests next action.