_docs_vivas

A shared documentation guide for Alfred Dev workflows. It defines which living project documents are created or updated at stages such as discussion, architecture, development, and release.

In plain words
What is it for?
Use it while planning, mapping, discussing, building, auditing, or shipping a project with Alfred Dev. It helps maintain the project index, architecture notes, decision records, threat model, and dependency documentation.
Why use it?
It prevents project knowledge from becoming scattered or outdated. Each workflow knows where to record decisions, architecture, security concerns, dependencies, and progress.

Command

Install

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.

agentmods
npx agentmods add commands/686f6c61/alfred-dev/_docs_vivas
Clone the repo
git clone --depth 1 https://github.com/686f6c61/alfred-dev
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 772 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.00772
Opus 5 $0.00009 $0.00386
Sonnet 5 $0.00003 $0.00154
Haiku 4.5 $0.00002 $0.00077

Measured 2d ago against content hash 3c252e488b4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

_docs_vivas 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.

commands/_docs_vivas.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentación viva del proyecto

Protocolo compartido. Lo leen feature, fix, quick, spike, audit, ship, map-codebase y discuss. No es un slash command.

Paso 0 -- esqueleto

Antes de la primera fase (o al mapear / discutir), ejecuta:

python3 .claude/alfred-continuity.py sync-project-docs "$PWD"

Eso crea, si faltan:

  • docs/project/README.md (índice)
  • docs/project/architecture.md
  • docs/project/compliance.md
  • docs/project/threat-model.md
  • docs/project/dependencies.md
  • docs/adr/

No rellena prosa. Los esqueletos llevan <!-- alfred-doc:scaffold -->.

Qué se toca en cada momento

Solo actualiza lo que la fase ha cambiado. No reescribas el resto.

Momento Quién Ficheros
discuss Alfred índice (existe) + discovery.md
map-codebase helper + Alfred índice + esqueleto de arquitectura
Producto aprobado product-owner PRD; el índice se refresca
Arquitectura architect + security-officer architecture.md (relleno), ADR si hay decisión, threat-model.md (relleno)
Dependencia nueva architect o security-officer dependencies.md
Desarrollo / quick / fix tech-writer (sync corto) + senior-dev índice; cabeceras/docstrings del código tocado; current.md
Calidad / audit security-officer compliance.md con evidencia
Documentación de cierre / ship tech-writer índice, CHANGELOG, release notes
Pausa helper handoff (sin tocar architecture/compliance)

Antes de cerrar una gate

python3 .claude/alfred-continuity.py check-project-docs "$PWD" --command <comando> --phase <fase>

Si el helper sale distinto de 0, la gate no se declara superada. Rellena el hueco y vuelve a comprobar.

Un documento cuenta como relleno cuando tiene <!-- alfred-doc:filled --> o cuando ya existía con contenido real (sin marcador de esqueleto).

ADR

Si la fase de arquitectura (o un spike) toma una decisión nueva:

python3 .claude/alfred-continuity.py next-adr "$PWD" --title "Título corto de la decisión"

Read the full file on GitHub · 85 lines

Changes

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.

  1. 2d ago First seen · 85 lines · 17 tokens per session scan A 3c252e488b4b

Subscribe to this mod's changes

_docs_vivas is a command published in the GitHub repository 686f6c61/alfred-dev (119 stars, last pushed 18d ago), licensed MIT. It adds 17 tokens to every session and 772 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.