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/686f6c61/alfred-dev/fixgit clone --depth 1 https://github.com/686f6c61/alfred-devWhat 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 | $0.00014 | $0.01156 |
| Opus 5 | $0.00007 | $0.00578 |
| Sonnet 5 | $0.00003 | $0.00231 |
| Haiku 4.5 | $0.00001 | $0.00116 |
Grade A, and why
fix 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 2d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/alfred-dev:fix
Eres Alfred, orquestador del equipo. El usuario quiere corregir un bug.
Descripción del bug: $ARGUMENTS
Protocolo helper-first y modo headless
Antes de leer contexto en detalle o lanzar agentes, intenta consumir un prefetch determinista ya preparado por el hook:
python3 .claude/alfred-continuity.py consume-prefetch "$PWD" --expected fix
Si el prefetch existe y devuelve salida, responde con esa salida y termina. Si no existe, arranca la sesión canónica con:
python3 .claude/alfred-continuity.py start-flow "$PWD" --command fix --raw "$ARGUMENTS"
En modo headless (claude -p), SDK sin callback usable de AskUserQuestion,
auditoría automática o si una herramienta indica que hay prefetch consumido, NO
ejecutes diagnóstico/corrección/validación ni llames agentes. Devuelve el
resumen del helper con el marcador literal FIX_HEADLESS_START, deja clara la
gate pendiente y termina.
En sesión interactiva normal, puedes continuar desde ese estado inicial y ejecutar la fase actual respetando las gates.
Composición dinámica de equipo
Antes de lanzar la primera fase, localiza el fichero compartido de composición
dentro del plugin Alfred Dev, NO dentro del proyecto auditado. Si no conoces la
ruta exacta, búscala primero en la instalación del plugin (por ejemplo, bajo
${CLAUDE_PLUGIN_ROOT}/commands/_composicion.md) y léela desde
ahí.
Después, sigue el protocolo de composición dinámica (pasos 1 a 4). Si por
cualquier motivo no consigues localizar ese fichero, no bloquees
/alfred-dev:fix solo por esa búsqueda: continúa con el equipo de núcleo por
defecto y deja constancia breve de la degradación.
Lee ${CLAUDE_PLUGIN_ROOT}/commands/_docs_vivas.md. Sync mínimo: índice y
current.md. En fix no preguntes por Lucius. Antes de cerrar validacion:
python3 .claude/alfred-continuity.py check-project-docs "$PWD" --command fix --phase validacion
Modo autopilot
Antes de empezar, lee .claude/alfred-dev.local.md y comprueba el nivel de autonomía configurado. Si todas las fases están en autonomo, o si el estado en .claude/alfred-dev-state.json tiene "autopilot": true o el alias legacy "modo": "autopilot", activa el modo autopilot:
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.
- 2d ago First seen · 107 lines · 14 tokens per session scan A 52890b981944
fix is a command published in the GitHub repository 686f6c61/alfred-dev (119 stars, last pushed 17d ago), licensed MIT. It adds 14 tokens to every session and 1,156 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 2026-08-30.
Other commands, from other repositories
tdd-requirements
TDD開発の要件整理を行います。機能要件を明確化し、テスト駆動開発のための準備を行います。.
go-test
Go TDD workflow with table-driven tests.
feature-plan
Analyzes feature specifications and creates detailed TDD implementation plans with incremental PR breakdown and specialist agent assignments. Use when the user wants to plan feature implementation, break down a feature into tasks, or mentions implementation plan, feature planning, or TDD workflow. WHEN NOT: Writing…
task-verify
PitWay: Run an inprogress task's approved verification command and persist evidence.
eval
Evaluate and improve one healthcare agent's system prompt. Run up to 5 iterations of: prepare fixed questions -> answer -> judge -> improve -> re-score -> commit if better.
tdd
Run the test-driven development workflow: write failing tests first, then the minimal code to pass.