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 instructions/luisfurquim/wings/claude-mdgit clone --depth 1 https://github.com/luisfurquim/wingsWrote 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.
[](https://agentmods.dev/instructions/luisfurquim/wings/claude-md)<a href="https://agentmods.dev/instructions/luisfurquim/wings/claude-md"><img src="https://agentmods.dev/badge/instructions/luisfurquim/wings/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00535 | $0.00535 |
| Opus 5 | $0.00267 | $0.00267 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
wings CLAUDE.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 5d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — grafia: Índice Estruturado de Código
Este projeto usa grafia (índice SQLite de símbolos, referências e dependências).
Regra principal
Para localizar um símbolo (função, método, tipo, campo) e ver seu código:
grafia grep <nome> # declaração + todos os usos, COM o código-fonte
grafia grep <nome> --kind call # só chamadas
grafia grep <nome> -C 3 # com linhas de contexto
grafia grep <nome> --max 60 # mais resultados (default 40)
Símbolos homônimos? Use padrão pontuado — seleciona só o que você quer, sem regex de receiver:
grafia grep db.New # a New() do pacote db (não as dos outros pacotes)
grafia grep Router.Get # o Get() do tipo Router (não o dos outros tipos)
grafia grep internal/db.New # desambigua dois pacotes chamados db
Os padrões pontuados funcionam também em query symbol, query callers, query callees e query usages.
Uma chamada devolve a declaração completa e cada uso com arquivo:linha e a linha de código — não é preciso ler os arquivos para reconhecimento. O grafia grep detecta arquivos alterados e reindexa sozinho antes de responder; não é necessário rodar grafia update após cada edição.
Use grep/rg comum apenas para texto literal (strings, mensagens de erro, comentários).
Outros comandos (quando precisar)
grafia query callers <nome> # quem chama (JSON)
grafia query callees <nome> # o que chama (JSON)
grafia query file <path> # símbolos do arquivo (JSON)
grafia query deps <path> [--transitive] # imports (JSON)
grafia stats # visão geral do projeto
grafia sql "<query>" # SQL direto: files, symbols, refs, dependencies
grafia update --git-diff # sincronizar após pull/merge externo
Notas
- O banco fica em
.grafia.db(gitignored). Não edite esse arquivo. - Ao final de uma tarefa com muitas edições, rode
grafia update <arquivos editados>uma única vez (em lote). - Não é preciso verificar o índice após editar — ele se autocorrige na próxima consulta.
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.
- 5d ago First seen · 47 lines · 535 tokens per session scan A 6c450c9ea524
wings CLAUDE.md is an instructions file published in the GitHub repository luisfurquim/wings (29 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 535 tokens to every session, about $0.0027 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 instructions, from other repositories
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).
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.
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.
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.