Borrowing it
Nothing to install: this file belongs to hmaurus/skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hmaurus/skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/hmaurus/skillsWrote 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/hmaurus/skills/claude-md)<a href="https://agentmods.dev/instructions/hmaurus/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/hmaurus/skills/claude-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.
<a href="https://agentmods.dev/instructions/hmaurus/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/hmaurus/skills/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00988 | $0.00988 |
| Opus 5 | $0.00494 | $0.00494 |
| Sonnet 5 | $0.00198 | $0.00198 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
skills 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 today.
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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENT — Projeto aicf
O que é
Plugin de skills para Claude Code que cuida da governança e do planejamento macro de um projeto de software: PRD, checklist de entregas e demandas versionadas, e o ciclo que leva cada demanda da ideia ao registro do que foi feito.
Este repositório é a fonte editável do plugin, publicado no marketplace aicodingflow.
Lema
Simplicidade e manutenibilidade acima de tudo. Havendo trade-off entre a solução mais completa e a mais direta, escolher a direta — desde que entregue o resultado. Gatilho de revisão: dois mecanismos coexistindo, sincronização entre estados, ou abstração antecipando o futuro.
Refatoração contínua: trecho que ficou mais complexo com o tempo se simplifica antes de receber feature nova.
Registro
Memory é atalho do agente — quem precisa saber é o repositório. Decisões, IDs, gotchas e lições vivem em docs/, no CLAUDE.md e no código. Memory pode sumir ou ficar desatualizada; validar contra o repositório antes de confiar.
Exceção: credenciais ficam em .env (não commitado) ou no gerenciador de senhas. Nunca no repositório, nunca em memory.
Glossário do domínio (CONTEXT.md) e decisões difíceis de reverter (ADR em docs/adr/, numerado e imutável) nascem quando houver o primeiro termo ambíguo ou a primeira decisão a registrar — o passo 4 do ritual de fechamento manda escrever nos dois.
Este arquivo é lido inteiro em toda sessão. O alvo que a documentação do Claude Code publica é abaixo de 200 linhas; regra que só vale para uma parte do código vai para .claude/rules/<tema>.md com paths: no frontmatter, e procedimento de vários passos vira skill. /doctor propõe cortes do que o agente já deduz do código.
Processos de desenvolvimento
Duas camadas: a governança registra o que será feito e o que foi feito, e é sempre a mesma; a implementação é como o código sai, e tem caminhos à escolha. Uma demanda passa por quatro fases: demanda → entrevista → implementação → fechamento.
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.
- today Changed · +1 lines · +49 tokens per session 815e522e6ac4
- yesterday First seen · 54 lines · 939 tokens per session scan A 4f6d43317364
skills CLAUDE.md is an instructions file published in the GitHub repository hmaurus/skills (3 stars, last pushed today), licensed MIT. It adds 988 tokens to every session, about $0.0049 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 2026-09-08.
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.
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 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).
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.