What is claw-pilot CLAUDE.md?

Project-specific instructions for developing claw-pilot, a command-line tool and web dashboard that manages multiple AI-agent processes on Linux or macOS servers.

Use them when working on claw-pilot’s command line, web dashboard, agent lifecycle management, database, or tests. They also state that the project is installed from source rather than npm.

They give the agent the project’s architecture, supported tools, language rules, and testing commands, reducing guesswork during code changes.

How swoelffel/claw-pilot configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to swoelffel/claw-pilot. 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/swoelffel/claw-pilot/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/swoelffel/claw-pilot

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/swoelffel/claw-pilot/claude-md/github.svg)](https://agentmods.dev/instructions/swoelffel/claw-pilot/claude-md)

Your own site

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

Per session 4,156 This file is loaded in full into every session.

When invoked 4,156 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	$0.04156	$0.04156
Opus 5.5	$0.01662	$0.01662
Sonnet 5.5	$0.00831	$0.00831
Haiku 4.5	$0.00416	$0.00416

Measured 20d ago against content hash c33494095a0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claw-pilot CLAUDE.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 20d 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.

CLAUDE.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this project is

claw-pilot v0.84.14 — CLI + web dashboard that orchestrates multiple claw-runtime agent instances on a Linux or macOS server. It handles discovery, provisioning, lifecycle management, permanent cross-channel sessions, and extensible middleware pipeline.

All instances use the claw-runtime engine — a native Node.js engine (src/runtime/), managed via PID file daemon.

Not published on npm — installed from source only (/opt/claw-pilot). GitHub: https://github.com/swoelffel/claw-pilot

Tech stack

Runtime: Node.js 22.23.3 LTS reference (.nvmrc); declared compatibility >= 22.12.0, ESM, pnpm
CLI: Commander.js + @inquirer/prompts
HTTP/WS: Hono + ws
DB: better-sqlite3 (SQLite, WAL mode, schema v58)
UI: Lit web components + Vite
Build: tsdown (CLI) + vite (UI)
Tests: Vitest
Lint: oxlint
LLM SDK: Vercel AI SDK ai v7.x

Language standard

All documentation and code comments must be written in English. Commit messages follow conventional commits in English. Exception: DB migration context and UI localization strings may reference French for historical reasons.

Contribution workflow

See CONTRIBUTING.md for the full contributor guide. The three non-negotiable rules:

Branch off develop, PR against develop — never main. main is reserved for release PRs.
Never bump package.json version in a feature PR — reserved for the release PR (develop → main).
Never skip lefthook hooks (--no-verify) — CI enforces the same checks and will reject the PR.

Key commands

pnpm build:cli     # Build CLI only (dist/)
pnpm build         # Build CLI + UI
pnpm build:safe    # typecheck:all then build
pnpm test:run      # Run tests once
pnpm test:e2e      # Run e2e tests (real HTTP server, in-memory DB)
pnpm typecheck     # tsc --noEmit
pnpm typecheck:all # tsc --noEmit (backend + UI)
pnpm lint          # oxlint src/
pnpm lint:all      # oxlint src/ + ui/src/
pnpm format        # prettier --write
pnpm format:check  # prettier --check (CI mode)
pnpm spellcheck    # cspell (en + fr dictionaries)
pnpm knip          # Dead code detection
pnpm check:circular # Circular dependency check via madge

Read the full file on GitHub · 300 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.

20d ago Changed c33494095a0d
21d ago Changed 6a860066bd9e
22d ago Changed c1ea5450da02
28d ago Changed 3563d6402e5b
29d ago Changed · +14 tokens per session ccb6922feefd
1mo ago Changed 767062aad029
2mo ago First seen · 300 lines · 4,142 tokens per session scan A 1f4f32e7dc66

Subscribe to this mod's changes

claw-pilot CLAUDE.md is an instructions file published in the GitHub repository swoelffel/claw-pilot (11 stars, last pushed 21d ago), licensed MIT. It adds 4,156 tokens to every session, about $0.0166 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.

agent-orchestration agentic ai-agents anthropic claude dashboard

claw-pilot CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claw-pilot CLAUDE.mdswoelffel/claw-pilot	Instructions file	11	21d ago	MIT	A	4,156	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

claw-pilot: Instructions file for Claude Code