Borrowing it
Nothing to install: this file belongs to 0xAI-Builders/comandos. 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/0xAI-Builders/comandos/main/CLAUDE.mdgit clone --depth 1 https://github.com/0xAI-Builders/comandosWrote 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/0xai-builders/comandos/claude-md)<a href="https://agentmods.dev/instructions/0xai-builders/comandos/claude-md"><img src="https://agentmods.dev/badge/instructions/0xai-builders/comandos/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/0xai-builders/comandos/claude-md"><img src="https://agentmods.dev/badge/instructions/0xai-builders/comandos/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 | $0.00555 | $0.00555 |
| Opus 5.5 | $0.00222 | $0.00222 |
| Sonnet 5.5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade C, and why
comandos CLAUDE.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 22d 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.
- Nunca `rm -rf` del directorio del socket antes del `kill-server`; primero What it actually says
Reglas para agentes en este repo
tmux: nunca el servidor del usuario
Las sesiones de trabajo de Jesús (20+ agentes) viven en el tmux default de
/tmp/tmux-1000. Un kill-server ahí las mata todas (pasó el 2026-10-04).
- Todo tmux de prueba va con socket explícito:
tmux -S <dir>/tmux-1000/defaulto-L <etiqueta-propia>.TMUX_TMPDIRsolo no sirve: tmux 3.2a lo ignora en silencio si el directorio no existe y cae en/tmp/tmux-1000/default. - Nunca
rm -rfdel directorio del socket antes delkill-server; primerokill-server, después borrar. - En Rust usa
Tmux::private(dir)(crates/comandos-server/src/dash/native/tmux.rs) y enxtaskprivate_tmux(dir): ya pasan-S. - Prohibido
tmux kill-server,kill-session,pkill tmuxokill -9 -1sin-S/-Lpropio, aunque sea «para probar».
Compilaciones: caché compartida con presupuesto
- Todas las compilaciones de migración en Linux pasan por /home/someguy/codebase/0xJesus/ComandOS/.worktrees/rust-integration-acp/scripts/rust-build-cache. El runner aislado ya incorpora esa comprobación.
- Los worktrees comparten /home/someguy/codebase/0xJesus/ComandOS/.build/target-integration-acp. No crear un target por agente, revisión o intento ni cambiar de target para saltarse un rechazo del presupuesto. Ejecutar un solo Cargo a la vez.
- El runner rechaza opciones de salida o configuración que puedan cambiar ese
target; no pasar
--target-dirni--configa las comprobaciones. - Se comprueba la caché antes y después de cada comando. Con más de 32 GiB asignados o menos de 16 GiB libres se rechazan nuevas compilaciones. Es un control de admisión; una compilación puede exceder el límite mientras corre.
- Este control no borra artefactos ni detiene procesos. La limpieza requiere comprobar referencias y montajes de procesos activos y conservar binarios finales fuera de los targets. Preservar siempre sesiones, datos e historiales del usuario.
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.
- 22d ago Changed · +17 lines · +280 tokens per session c014fdf63f30
- 24d ago First seen · 17 lines · 275 tokens per session scan C a2b4a4548bac
comandos CLAUDE.md is an instructions file published in the GitHub repository 0xAI-Builders/comandos (6 stars, last pushed 22d ago), licensed MIT. It adds 555 tokens to every session, about $0.0022 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 2026-10-06.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.