agentmods.dev

ClawCrate AGENTS.md

ClawCrate AGENTS.md is an instructions file for Codex, OpenCode from manuelpenazuniga/ClawCrate. It costs 419 tokens per session, scanned A, original, MIT.

Project instructions for ClawCrate, a tool that runs AI-generated shell commands in restricted operating-system sandboxes. They describe its architecture, supported command modes, and engineering rules.

In plain words
What is it for?
Use them when implementing, reviewing, or planning changes in the ClawCrate repository. They cover its Linux and macOS sandboxing, command separation, profiles, network access, and filesystem artifacts.
Why use it?
They give a coding agent the project context and rules it must follow when changing ClawCrate. This reduces the risk of violating its security design or mixing up its supported modes.

Instructions file for CodexOpenCode

not rated 2 28d ago A scan 419 tokens original MIT
View the source file manuelpenazuniga/ClawCrate
Install

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.

agentmods
npx agentmods add instructions/manuelpenazuniga/clawcrate/agents-md
Clone the repo
git clone --depth 1 https://github.com/manuelpenazuniga/ClawCrate

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 ClawCrate AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/manuelpenazuniga/clawcrate/agents-md.svg)](https://agentmods.dev/instructions/manuelpenazuniga/clawcrate/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/manuelpenazuniga/clawcrate/agents-md"><img src="https://agentmods.dev/badge/instructions/manuelpenazuniga/clawcrate/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 419 This file is loaded in full into every session.
When invoked 419 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00419 $0.00419
Opus 5 $0.00210 $0.00210
Sonnet 5 $0.00084 $0.00084
Haiku 4.5 $0.00042 $0.00042

Measured 5d ago against content hash eccbf3d9c596, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ClawCrate 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 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.

AGENTS.md · 47 lines

What it actually says

AGENTS.md — ClawCrate context for Codex

This file is a concise, Codex-focused companion to CLAUDE.md.

Primary Sources

  • CLAUDE.md is the actionable source of truth for implementation.
  • clawcrate-v3.1.1.md is the full product/spec document.
  • README.md is external-facing positioning and usage docs.

Project Summary

ClawCrate is a native sandbox runtime for AI-generated shell commands:

  • Linux: Landlock + seccomp (+ rlimits)
  • macOS: Seatbelt (sandbox-exec) (+ rlimits)
  • No Docker, no VMs, no root required

Alpha scope: run, plan, doctor.

Non-Negotiable Architecture Rules

  1. Deny by default.
  2. Use platform-native sandboxing only.
  3. Command separation is always clawcrate run -- COMMAND....
  4. Profiles are the primary UX (safe, build, install, open).
  5. install defaults to Replica mode.
  6. Artifacts are filesystem-based (no SQLite in alpha).
  7. Keep DefaultMode (profile intent) separate from WorkspaceMode (materialized paths).
  8. Linux cannot reliably deny specific files inside an allowed workspace path; use Replica Mode for that.
  9. Network in alpha is coarse-grained: none or open only.
  10. ClawCrate sandboxes commands, not the whole agent process.

Engineering Guardrails

  • Keep clawcrate-types dependency-free and platform-agnostic.
  • Keep all #[cfg(target_os = ...)] inside clawcrate-sandbox.
  • No Tokio in alpha.
  • No HTTP client stack in alpha runtime.
  • Prefer simple file artifacts per execution:
    • plan.json
    • result.json
    • stdout.log
    • stderr.log
    • audit.ndjson
    • fs-diff.json
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. 5d ago First seen · 47 lines · 419 tokens per session scan A eccbf3d9c596

Subscribe to this mod's changes

ClawCrate AGENTS.md is an instructions file published in the GitHub repository manuelpenazuniga/ClawCrate (2 stars, last pushed 28d ago), licensed MIT. It adds 419 tokens to every session, about $0.0021 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 2026-08-31.

AI Safetyai-agentsai-securityaudit-trailcompliancedeveloper-tools
Related

Other instructions, from other repositories

permit0 CLAUDE.md

Instructions for permit0-ai/permit0, covering claude.md, commands, build, test (ci uses nextest) and run a single test.

permit0-ai/permit0 · 1,759 tokens

agent-governance-toolkit copilot-instructions.md

Copilot instructions for microsoft/agent-governance-toolkit, covering copilot instructions for agent-governance-toolkit, architecture, build, test, and lint, python and install (editable, all extras).

microsoft/agent-governance-toolkit · 5,833 tokens

node9-proxy CLAUDE.md

Claude Code instructions for node9-ai/node9-proxy, covering node9 proxy — claude code rules, pr checklist (required before every commit), test rules, code rules and architecture notes.

node9-ai/node9-proxy · 858 tokens

qwed-verification copilot-instructions.md

Copilot instructions for QWED-AI/qwed-verification: Read and follow QWEDRULES.md for every suggestion.

QWED-AI/qwed-verification · 155 tokens

claudini CLAUDE.md

Instructions for romovpa/claudini, covering claudini — developer guide, package manager, running benchmarks, run a preset (all methods, all samples) and override method, sample, seed, budget from cli.

romovpa/claudini · 1,257 tokens

leashd CLAUDE.md

Instructions for vmehera123/leashd, covering claude.md, commands, install dependencies, run tests (single file / specific test / all) and run tests with coverage.

vmehera123/leashd · 1,826 tokens