agentmods.dev

ClawCrate: Instructions file for Codex

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

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions Codex.

This is manuelpenazuniga/ClawCrate's own configuration. It tells Codex and OpenCode how to work on ClawCrate itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ClawCrate configures →

not rated 2repo 3mo ago A scan 419 tokens original MIT
View source ↗ manuelpenazuniga/ClawCrate
Reuse

Borrowing it

Nothing to install: this file belongs to manuelpenazuniga/ClawCrate. 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/manuelpenazuniga/ClawCrate/main/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/github.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/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.

agentmods 80×15 button for ClawCrate AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/manuelpenazuniga/clawcrate/agents-md"><img src="https://agentmods.dev/badge/instructions/manuelpenazuniga/clawcrate/agents-md.svg" alt="Reviewed on agentmods" width="80" 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. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00419 $0.00419
Opus 5.5 $0.00168 $0.00168
Sonnet 5.5 $0.00084 $0.00084
Haiku 4.5 $0.00042 $0.00042

Measured 2mo ago against content hash eccbf3d9c596, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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. 2mo 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 3mo ago), licensed MIT. It adds 419 tokens to every session, about $0.0017 per session on Opus 5.5. 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

ClawCrate AGENTS.md compared with instructions from other repositories

ClawCrate AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ClawCrate AGENTS.mdmanuelpenazuniga/ClawCrateInstructions file23mo agoMITA419Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot