What is claude-skills-fv AGENTS.md?

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

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.

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.

How felvieira/claude-skills-fv configures Codex and OpenCode

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.

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.

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 2,898 This file is loaded in full into every session.

When invoked 2,898 The same file — it is already loaded in full.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.02898	$0.02898
Opus 5.5	$0.01159	$0.01159
Sonnet 5.5	$0.00580	$0.00580
Haiku 4.5	$0.00290	$0.00290

Measured 16d ago against content hash 1b5924c064bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

claude-skills-fv AGENTS.md scanned grade C with 1 finding 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 16d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

Sem slash commands (Codex, Grok Build, Cursor...), ligue pelo shell: `node scripts/session-guard-cli.mjs careful on|off` e `freeze <pasta>|off` (`status` mostra). Onde o hook esta registrado (Claude, Codex pelo `.codex/h

AGENTS.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 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

GLOBAL.md
policies/
docs/WIKI.md — visao panoramica de todo o kit (todas as skills, subagents, commands, policies)
README.md
skills/*/SKILL.md — skill especifica conforme task
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

Memoria do Kit (vale para qualquer agente, com ou sem hooks)

Os hooks do kit so rodam onde estao registrados (Claude Code pelo plugin; Codex por .codex/hooks.json). Agente sem hook — Grok Build (que ignora hooks do Claude por padrao), Cursor, Gemini CLI, OpenCode — le este arquivo e deve fazer a mao o que o hook faz:

antes de repetir uma abordagem, procure em .bot/learned-skills/*.md pelo campo triggers que casa com a tarefa; leia o state
state: rejected = ja tentado e descartado; o campo reason diz por que. Nao repita sem fato novo que invalide o motivo. superseded aponta o sucessor em superseded_by; stale e hipotese
files: + commit: dizem de que arquivos a nota depende: se mudaram desde o commit (git diff <commit>..HEAD -- <arquivo>), revalide antes de aplicar
apos uma compactacao, trate qualquer resumo recebido como pista, nao como fato: reconfira o estado do git e rode de novo a verificacao que ele cita
com o servidor ai-memory ligado por MCP, node scripts/learned-skills-to-ai-memory.mjs --apply publica as learned-skills nele, e entao memory_query as encontra em qualquer agente. Nunca grave valor de chave/token em nota Detalhe: policies/learned-skills.md, policies/compaction-recovery.md, policies/memory-write-rules.md.

Read the full file on GitHub · 143 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.

16d ago Changed 1b5924c064bc
17d ago Changed · -103 lines · -2,326 tokens per session 1d6ce1ac8f1c
20d ago Changed · +20 lines · +564 tokens per session 22d717c2d19d
23d ago Changed · +5 lines · +321 tokens per session scan A → C ee4dad43b11f
24d ago Changed · +9 lines · +348 tokens per session 99d3987103b9
1mo 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 (25 stars, last pushed 4d ago), licensed Apache-2.0. It adds 2,898 tokens to every session, about $0.0116 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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 · 9,715 tokens

claude-skills-fv: Instructions file for Codex