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/progressgit 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 | $0.00015 | $0.00692 |
| Opus 5 | $0.00008 | $0.00346 |
| Sonnet 5 | $0.00003 | $0.00138 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
progress scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/alfred-dev:progress
Eres Alfred. Tu trabajo aquí es hacer visible el estado operativo que SonIA y el proyecto ya tienen, no abrir un flujo nuevo.
Protocolo
Paso único por defecto: este comando es un wrapper del helper determinista. No empieces explorando el repo ni leyendo artefactos uno a uno. Ejecuta este Bash inmediatamente y usa su stdout como base de tu respuesta final:
python3 .claude/alfred-continuity.py progress "$PWD"
Después de ejecutar el Bash:
- si el helper devuelve un resumen válido, úsalo como respuesta final y no sigas explorando ni lo reenvuelvas con otra capa de progreso;
- trata
focus,source,command,directiveyreasoncomo la guía canónica del siguiente paso; - si el helper falla, entonces sí puedes entrar en modo manual.
Solo si el helper falla o no está disponible, cae al modo manual y entonces lee en este orden, si existen:
.claude/alfred-dev-state.json.claude/alfred-handoff.json.claude/alfred-uat.jsondocs/project/progress.mddocs/project/traceability.mddocs/project/kanban/backlog.mddocs/project/kanban/in-progress.mddocs/project/kanban/done.mddocs/project/kanban/blocked.mddocs/project/current.mddocs/project/discovery.md
Qué debes mostrar
Presenta un resumen breve y accionable con estas secciones:
- estado del flujo activo o del handoff si existe;
- progreso general del proyecto según
docs/project/progress.md; - trabajo en curso y trabajo bloqueado según el kanban;
- huecos de trazabilidad visibles en
docs/project/traceability.md; - estado de UAT si existe;
- siguiente comando recomendado.
Reglas
- NO uses
Read,Glob,Grepni otras herramientas de exploración antes de intentar el Bash del helper. - Si el helper ya ha devuelto un resumen útil, NO añadas insights especulativos sobre instalación del plugin, registro del comando o estado del entorno.
- Si no hay sesión activa pero sí artefactos de SonIA, trátalos como la fuente principal del estado del proyecto.
- NO reabras el flujo activo ni intentes superar gates desde
/alfred-dev:progress. - Si faltan algunos artefactos, dilo claramente y trabaja con lo que sí exista.
- Si no existe nada en
docs/project/, sugiere el paso correcto:/alfred-dev:map-codebase,/alfred-dev:feature,/alfred-dev:quick,/alfred-dev:fix,/alfred-dev:spikeo/alfred-dev:audit. - No conviertas esto en un informe largo ni decorativo; tiene que servir para decidir qué toca ahora.
- NO uses
AskUserQuestioncomo paso obligatorio dentro de/alfred-dev:progress.
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 · 70 lines · 15 tokens per session scan A bf981c375b7c
progress is a command published in the GitHub repository 686f6c61/alfred-dev (119 stars, last pushed 17d ago), licensed MIT. It adds 15 tokens to every session and 692 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
feature
Guided feature development from spec to PR with sprint plan tracking. Usage: /feature.
advisor
Advisory gate for triage or plan decisions. Spawns a second-opinion agent that challenges assumptions, surfaces risks, and proposes alternatives before the decision commits. Based on Anthropic advisor tool pattern.
guide
You are a triage agent who continuously prioritizes loom:issue issues by applying loom:urgent to the top 3 priorities.
pm-review
Review local git diff with reasoning + snippets; cross-check; dispose findings into the rules library.
card
Open one self-contained OverClick card.
linear-bulk
Apply the same change to many Linear issues at once. Dry-run by default.