claude-skills-fv: Instructions file for Codex

AGENTS.md

claude-skills-fv AGENTS.md is an instructions file for Codex, OpenCode from felvieira/claude-skills-fv. It costs 3,991 tokens per session, scanned A, original, Apache-2.0.

A set of instructions for coding agents working with a shared kit of skills, rules, and workflows across tools such as Claude and OpenCode.

In plain words
What is it for?
Use it to set up AGENTS.md in a project, install the kit in .bot/, guide agents through its policies and skills, and keep changes small and reviewable.
Why use it?
It gives agents a consistent reading order, safe defaults, and repository rules, so they are less likely to skip important guidance or make risky changes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is felvieira/claude-skills-fv's own configuration. It tells Codex and OpenCode how to work on claude-skills-fv itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-skills-fv configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is cp -r templates/stack-default/ ../meu-projeto/.

Reuse

Borrowing it

Nothing to install: this file belongs to felvieira/claude-skills-fv. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/felvieira/claude-skills-fv/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/felvieira/claude-skills-fv

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for claude-skills-fv AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/felvieira/claude-skills-fv/agents-md/github.svg)](https://agentmods.dev/instructions/felvieira/claude-skills-fv/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/felvieira/claude-skills-fv/agents-md"><img src="https://agentmods.dev/badge/instructions/felvieira/claude-skills-fv/agents-md/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.

agentmods 80×15 button for claude-skills-fv AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/felvieira/claude-skills-fv/agents-md"><img src="https://agentmods.dev/badge/instructions/felvieira/claude-skills-fv/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,991 This file is loaded in full into every session.
When invoked 3,991 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.03991 $0.03991
Opus 5 $0.01996 $0.01996
Sonnet 5 $0.00798 $0.00798
Haiku 4.5 $0.00399 $0.00399

Measured 11d ago against content hash c5c3c3181ff6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

claude-skills-fv AGENTS.md 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 11d 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.

AGENTS.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Objetivo

Este repositorio define um kit de skills e governanca para agentes de coding em Claude, OpenCode e superficies compativeis.

Uso em Repos Consumidores

  • em repos de aplicacao, o modo recomendado e manter AGENTS.md na raiz e instalar o kit dentro de .bot/
  • usar templates/AGENTS-root.md como base para o AGENTS.md do repo consumidor
  • se o repo consumidor nao tiver auditoria valida, iniciar por Repo Auditor

Ordem de Leitura

  1. GLOBAL.md
  2. policies/
  3. docs/WIKI.md — visao panoramica de todo o kit (todas as skills, subagents, commands, policies)
  4. README.md
  5. skills/*/SKILL.md — skill especifica conforme task
  6. docs/skill-guides/ somente quando a tarefa exigir exemplos extensos

Defaults Operacionais

  • responder curto por padrao
  • agir primeiro quando houver default seguro
  • nao repetir contexto desnecessario
  • usar tools com minimo privilegio
  • pedir aprovacao para acoes destrutivas ou externas de alto risco
  • registrar handoff curto e objetivo

Mudancas no Repositorio

  • prefira mudancas pequenas e revisaveis
  • preserve a hierarquia global do kit
  • nao reintroduza acoplamento a vendor ou comando especifico sem necessidade
  • mova exemplos longos para docs/skill-guides/ quando uma skill comecar a inflar

Validacao Minima

  • siga policies/evals.md para mudancas de skills, prompts e tools
  • siga policies/tool-safety.md para MCP, rede, escrita e acoes externas

Slash Commands

Atalhos por fase de desenvolvimento — use em vez de lembrar nomes de skills:

Command O que faz
/spec Especificar feature com critérios de aceitação
/plan Classificar task e montar pipeline
/build Implementar com stack do projeto
/test Escrever e rodar testes
/review Review final + security audit
/simplify Simplificar e refatorar código
/ship Release e deploy
/pipeline Pipeline completo end-to-end
/best Auditoria de boas práticas, clean code e DRY
/auto Agente autônomo — executa task completa sem intervenção
/loop Loop autônomo v2 — multi-agente (claude/codex), worktree paralelo, polishing pass (node scripts/auto-loop.mjs "task")
/worktree Cria git worktree isolado, copia .env*, valida ambiente em background
/detective-spec Engenharia reversa de specs em legado — extrai contratos sem tocar no código (skill 33)
/catalog-project Sintetiza repo-audit + detective-spec + narrativa de produto (resumo/planos/FAQ) + histórico de sessões + dados operacionais (envs/endereços/métricas) em .project-memory/manifest.yaml versionado no repo consumidor — tudo sempre rastreável a evidência, alimenta o catálogo cross-repo project-brain
/grill-me Interrogatório relentless de plano até convergência (uma pergunta + resposta sugerida por turno)
/to-prd Converte conversa atual em PRD publicado no issue tracker (label needs-triage)
/to-issues Quebra PRD em N issues independentes (vertical slices) e publica no tracker
/pipeline-discovery Pipeline COMPLETO discovery: grill-me → to-prd → to-issues → loop+TDD → ship
/constitution Bootstrap/update memory/constitution.md com princípios governantes (Code Quality, Testing, UX, Performance, Security)
/checklist Checklist contextual por feature ("unit tests for English") — Completeness, Clarity, Consistency, Coverage, Edge Cases
/analyze Cross-artifact consistency check (read-only) entre constituição → spec → plan → issues. CRITICAL bloqueia /build
/humanize Remove os 29 padrões de AI-generated writing de qualquer prosa (docs, PRDs, copy, changelogs)
/consolidate-memory Manutenção do vault de memória persistente — merge duplicatas, archive stale, prune índice. Workflow seguro com snapshot
/savings (v2.4.0) Mostra o que o kit salvou na sessão/janela: tokens economizados, USD, riscos prevenidos, hot files, decisões do gate. Auditoria em policies/savings-metrics.md. Mini-resumo automático no Stop hook.
/drift-scan (v2.5.0) Continuous drift detection contra todo o codebase: dead-code, large-files, stale-todos, dep-staleness, doc-code drift, test-coverage. Inspirado em Birgitta Böckeler — ver docs/inspiration/harness-engineering.md.
/context-budget (v2.26.0) Audita peso de contexto carregado na sessão: skills/agents/MCP/rules/CLAUDE.md — tokens estimados por componente, headroom disponível, alertas de overflow. Distinto do /savings (que rastreia completions runtime).
/spec-kit (v2.28.0) Pipeline SDD unificado: specify → plan → tasks → implement com checkpoints explícitos e Adversarial Verifier inline. Inspirado no GitHub Spec Kit (88k stars). --phase specify / --phase plan / --skip-checkpoints para CI.
/insights (v2.28.0) Recomendações baseadas em uso real: lê JSONLs de telemetria dos hooks (gate decisions, investigate-first bloqueios, tool repetitions, conflict-resolutions) e recomenda o que calibrar. Similar ao /Insights nativo mas lê dados do kit.
/run-program Executa pipeline declarativo YAML (programs/*.yml) com 7 step types (command/prompt/bash/gate/loop/parallel/conditional), context: fresh per step, provider/model routing, trigger_rule para parallel. 6 programs: pipeline-discovery, spec-driven-development, loop-polishing, detective-spec, adversarial-dev (GAN), comprehensive-review (5-agent parallel)
(auto) Auto-orchestration (v1.8.0): hook intent-classifier sugere program adequado baseado em intent do prompt. Skill 39 (program-router) confirma. 4 níveis de autonomia em policies/auto-orchestration.md
/swarm TOTAL AUTONOMY (v2.0.0): do prompt ao PR mergeable. Worktree isolado + Ralph loop (fresh context per story) + 4-agent parallel review + self-fix CRITICAL/HIGH + auto PR. Em modo Autonomous (Nível 3), o hook auto-roteia features pra /swarm. Inspirado em Ralph/fix-issue/comprehensive-review do archon.
(via /run-program) refactor-safely (v2.1.0): pipeline com behavior preservation — baseline tests + analyze read-only + atomic plan + execute com type-check hooks + verify + PR. Use pra refactor de módulos grandes.
(doc) docs/USE-CASES.md (v2.1.0): mapeia 17 cenários de dev no dia-a-dia → comando apropriado. Hook intent-classifier v2 roteia auto baseado nesses cenários.

Read the full file on GitHub · 212 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. 11d ago First seen · 212 lines · 3,991 tokens per session scan A c5c3c3181ff6

Subscribe to this mod's changes

claude-skills-fv AGENTS.md is an instructions file published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,991 tokens to every session, about $0.0200 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens