What is ClawLite AGENTS.md?

A repository guide for ClawLite, including its project rules, commands, validation workflow, important paths, and instructions for working with GitHub issues and pull requests.

Use it when answering questions about ClawLite, changing its code, validating the project, or creating GitHub issue and pull-request updates.

It gives coding agents verified repository-specific guidance and avoids common mistakes when writing chat responses or GitHub messages.

How eobarretooo/ClawLite configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to eobarretooo/ClawLite. 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/eobarretooo/ClawLite/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/eobarretooo/ClawLite

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/eobarretooo/clawlite/agents-md/github.svg)](https://agentmods.dev/instructions/eobarretooo/clawlite/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/eobarretooo/clawlite/agents-md"><img src="https://agentmods.dev/badge/instructions/eobarretooo/clawlite/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/eobarretooo/clawlite/agents-md"><img src="https://agentmods.dev/badge/instructions/eobarretooo/clawlite/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,882 This file is loaded in full into every session.

When invoked 3,882 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.

Model	Per session	Once invoked
Fable 5.1	$0.03882	$0.03882
Opus 5.5	$0.01553	$0.01553
Sonnet 5.5	$0.00776	$0.00776
Haiku 4.5	$0.00388	$0.00388

Measured 2mo ago against content hash 64a502ba49fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ClawLite 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 · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — ClawLite Repo Guide

Repo: https://github.com/renan/ClawLite (update with real URL)
In chat replies, file references must be repo-root relative only (example: clawlite/channels/telegram.py:80); never absolute paths.
GitHub issues/comments/PR bodies: use literal multiline strings or -F - <<'EOF' for real newlines; never embed \n as text.
GitHub comment footgun: never use gh issue/pr comment -b "..." when body contains backticks or shell chars. Always use -F - <<'EOF' heredoc.
When working on a GitHub Issue or PR, print the full URL at the end of the task.
When answering questions, respond with high-confidence answers only: verify in code; do not guess. It captures the repo's actual commands, validation workflow, and coding style.

Priority

Follow safety and applicable law.
Follow the user's explicit request.
Follow repository-specific guidance in this file.
Prefer small, auditable changes over broad refactors.

Core behavior inherited from the previous local guide:

Be objective, technical, and useful.
Ask questions only when critical information is missing.
Prefer execution plus verifiable results.
Validate with tests or smoke checks when practical.
Explain change impact clearly.
Never expose secrets or use destructive commands casually.

Rule Files Found

Root guidance exists in this AGENTS.md.
No .cursor/rules/ directory was found.
No .cursorrules file was found.
No .github/copilot-instructions.md file was found.

Repo Snapshot

Language: Python.
Packaging: pyproject.toml with setuptools.
Python: >=3.10.
Package: clawlite.
CLI entrypoint: clawlite = clawlite.cli:main.
Gateway: FastAPI + uvicorn + WebSocket support.
Runtime autonomy already includes supervised background loops for heartbeat, autonomy, channels_dispatcher, channels_recovery, subagent_maintenance, and self_evolution.
Tests: pytest.
Logging: loguru with helpers in clawlite/utils/logging.py.
CI covers Python 3.10 and 3.12.

Read the full file on GitHub · 292 lines

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.

2mo ago First seen · 292 lines · 3,882 tokens per session scan A 64a502ba49fd

Subscribe to this mod's changes

ClawLite AGENTS.md is an instructions file published in the GitHub repository eobarretooo/ClawLite (51 stars, last pushed 4mo ago), licensed MIT. It adds 3,882 tokens to every session, about $0.0155 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 2026-08-30.

Multi-Agent ai assistant linux mcp termux

ClawLite AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ClawLite AGENTS.mdeobarretooo/ClawLite	Instructions file	51	4mo ago	MIT	A	3,882	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

ClawLite: Instructions file for Codex