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.
npx agentmods add commands/doncheli/don-cheli-sdd/autogit 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/auto)<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/auto"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/auto.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.01622 |
| Opus 5 | $0.00036 | $0.00811 |
| Sonnet 5 | $0.00015 | $0.00324 |
| Haiku 4.5 | $0.00007 | $0.00162 |
Grade A, and why
auto 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 yesterday.
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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dc:auto — Modo Autónomo
Objetivo
Ejecutar el pipeline SDD completo sin intervención humana: research → spec → plan → code → test → verify → commit. Cada fase usa un agente fresco para evitar context rot.
Uso
/dc:auto "Implementar autenticación JWT con refresh tokens"
/dc:auto --nivel 2 # Forzar nivel específico
/dc:auto --hasta implementar # Parar después de una fase
/dc:auto --dry-run # Simular sin ejecutar código
/dc:auto --max-iteraciones 5 # Límite de ciclos TDD
/dc:auto --presupuesto 10.00 # Límite de costo en USD
Arquitectura Anti-Context-Rot
El problema fundamental: ejecutar todo en un solo contexto degrada la calidad.
Solución: Agentes frescos por fase.
Orquestador (30-40% del contexto — zona óptima)
│
├── Agente 1: RESEARCH (contexto fresco 200K)
│ └── Explora codebase, identifica constraints
│ Output → .dc/auto/research.md
│
├── Agente 2: SPECIFY (contexto fresco 200K)
│ └── Lee research.md → genera specs Gherkin
│ Output → .dc/specs/*.feature
│
├── Agente 3: PLAN (contexto fresco 200K)
│ └── Lee specs → genera blueprint técnico
│ Output → .dc/blueprints/*.md
│
├── Agente 4: BREAKDOWN (contexto fresco 200K)
│ └── Lee blueprint → genera tareas TDD
│ Output → .dc/tareas/*.md
│
├── Agentes 5-N: IMPLEMENT (contexto fresco por tarea)
│ └── Una tarea a la vez: RED → GREEN → REFACTOR
│ Output → código + tests
│
└── Agente Final: REVIEW (contexto fresco 200K)
└── Lee todo → peer review 7 dimensiones
Output → .dc/reviews/*.md
Cada agente:
- Inicia con contexto 100% limpio
- Lee SOLO los artefactos que necesita del disco (.dc/)
- Escribe su output a disco antes de terminar
- El orquestador decide si avanzar o reintentar
State Machine
┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐
│ RESEARCH │───▶│ SPECIFY │───▶│ PLAN │───▶│BREAKDOWN │
└──────────┘ └──────────┘ └──────────┘ └──────────┘
│
┌──────────┐ ┌──────────┐ │
│ REVIEW │◀───│IMPLEMENT │◀────┘
└──────────┘ └──────────┘
│ │
┌────▼────┐ ┌────▼────┐
│ DONE │ │ RETRY │──(max 3)
└─────────┘ └─────────┘
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.
- yesterday First seen · 178 lines · 73 tokens per session scan A 16f0af9f2d28
auto is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 24d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,622 once invoked, about $0.0004 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-phase
Add phase to end of current milestone in roadmap.
insert-phase
Insert urgent work as decimal phase (e.g., 72.1) between existing phases.
join-discord
Join the PBR Discord community.
new-milestone
Start a new milestone cycle — update PROJECT.md and route to requirements.
add-todo
Capture idea or task as todo from current conversation context.
audit-milestone
Audit milestone completion against original intent before archiving.