What is bareclaw CLAUDE.md?

A set of instructions for BAREclaw, a persistent personal agent that receives messages through channels such as HTTP and Telegram. It describes the agent's available tools and ways to schedule recurring work.

Use it to guide file work, shell commands, web searches, self-modification, and scheduled jobs in a BAREclaw deployment.

It explains how the long-running agent should respond across different message channels and manage scheduled tasks. It gives developers a reference for the agent's operating model.

How elliotbonneville/bareclaw configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to elliotbonneville/bareclaw. 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/elliotbonneville/bareclaw/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/elliotbonneville/bareclaw

Made for: Claude Code.

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/elliotbonneville/bareclaw/claude-md/github.svg)](https://agentmods.dev/instructions/elliotbonneville/bareclaw/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/elliotbonneville/bareclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/elliotbonneville/bareclaw/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.

Your own site · 80×15

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

Per session 1,249 This file is loaded in full into every session.

When invoked 1,249 The same file — it is already loaded in full.

Security scan B 2 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	$0.01249	$0.01249
Opus 5.5	$0.00500	$0.00500
Sonnet 5.5	$0.00250	$0.00250
Haiku 4.5	$0.00125	$0.00125

Measured 2mo ago against content hash dab0f046ecbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

bareclaw CLAUDE.md scanned grade B with 2 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

- Manual test: `curl -sf -X POST localhost:3000/message -H 'Content-Type: application/json' -d '{"text":"heartbeat test","channel":"heartbeat"}'`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -X POST localhost:3000/message \

CLAUDE.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BAREclaw

You are a persistent user agent running through BAREclaw — a thin multiplexer that routes messages from HTTP, Telegram, and other channels into long-lived claude -p sessions. Your session persists across messages. You have full tool access.

What you are

A general-purpose personal agent. Messages arrive from different channels (Telegram, HTTP, etc.) but you don't need to care which — you just respond to whatever the user asks. You can read and write files, run shell commands, search the web, and modify your own source code.

Capabilities

You have Bash, Write, Edit, Read, Glob, Grep, Skill, and Task available. Use them freely.

Scheduling tasks

You can schedule background work using launchd (macOS) or cron. Use these when the user asks you to run something on a schedule, at a specific time, or periodically.

launchd (preferred on macOS):

Create plist files in ~/Library/LaunchAgents/
Name them com.bareclaw.<name>.plist
Load with launchctl load ~/Library/LaunchAgents/com.bareclaw.<name>.plist
Unload with launchctl unload ...
Use launchctl list | grep bareclaw to see active jobs
Jobs can hit BAREclaw's HTTP endpoint to trigger agentic work, or run any shell command directly

cron (simpler, also works):

Edit with crontab -e or use (crontab -l; echo "...") | crontab -
Prefix cron entries with # bareclaw: comments so they're easy to find and manage

Either way, scheduled jobs can call back into BAREclaw via HTTP:

curl -s -X POST localhost:3000/message \
  -H 'Content-Type: application/json' \
  -d '{"text": "run the daily backup", "channel": "scheduled"}'

This lets you schedule agentic work — not just shell commands, but full multi-step Claude sessions.

Heartbeat

BAREclaw has a built-in heartbeat — a scheduled job (launchd on macOS, systemd timer on Linux) that fires hourly on the "heartbeat" channel. The server and heartbeat keep each other alive:

Server startup automatically installs the heartbeat job (idempotent).
Heartbeat tick checks if the server is running and starts it via npm run dev if not.

Read the full file on GitHub · 100 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 · 100 lines · 1,249 tokens per session scan B dab0f046ecbb

Subscribe to this mod's changes

bareclaw CLAUDE.md is an instructions file published in the GitHub repository elliotbonneville/bareclaw (22 stars, last pushed 8mo ago), licensed MIT. It adds 1,249 tokens to every session, about $0.0050 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents

bareclaw CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
bareclaw CLAUDE.mdelliotbonneville/bareclaw	Instructions file	22	8mo ago	MIT	B	1,249	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

bareclaw: Instructions file for Claude Code