Borrowing it
Nothing to install: this file belongs to punt-labs/beadle. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/punt-labs/beadle/main/CLAUDE.mdgit clone --depth 1 https://github.com/punt-labs/beadleWrote 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.
[](https://agentmods.dev/instructions/punt-labs/beadle/claude-md)<a href="https://agentmods.dev/instructions/punt-labs/beadle/claude-md"><img src="https://agentmods.dev/badge/instructions/punt-labs/beadle/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.
<a href="https://agentmods.dev/instructions/punt-labs/beadle/claude-md"><img src="https://agentmods.dev/badge/instructions/punt-labs/beadle/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.02344 | $0.02344 |
| Opus 5.5 | $0.00938 | $0.00938 |
| Sonnet 5.5 | $0.00469 | $0.00469 |
| Haiku 4.5 | $0.00234 | $0.00234 |
Grade A, and why
beadle 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
beadle
Autonomous agent daemon with cryptographic owner control. GPG-signed instructions, declared permissions, tamperproof audit trail. Runs on the owner's machine as a background daemon. Written in Go.
The shipping component is beadle-email — an MCP server for email communication via Proton Bridge with a four-level PGP trust model.
What Beadle Is
Beadle gives an AI agent its own email address and mailbox — it is not a tool for managing a human's personal inbox. Once an agent has a mailbox, email becomes a channel other parties can use to instruct it, with no live session required. Everything in the trust model exists to answer one question for that channel: who is allowed to direct this agent, and how much authority does a given message actually carry.
Two independent mechanisms decide that. There is no privileged "owner" role sitting above them — do not model one when reasoning about this system:
- Message verification — the four-level trust classification (
trusted/verified/untrusted/unverified, seedocs/ARCHITECTURE.md's "Trust Model" section), proving how hard a given message would be to forge.verifyTrustitself only classifies; the one place that result is actually enforced as a hard requirement isinternal/daemon/handler.go'sOnNewMailcall site (if trust != channel.Verified && trust != channel.Trusted { continue }) — no mission is created below that bar. Elsewhere,beadle-email'slist_messages/read_message/check_trustcompute and show the same classification, andreply_messagestill checks only permission before sending — nothing in any of these tools refuses to act because a message sits on a lower trust rung; it's a signal for the agent's own judgment. - Per-contact permission grants (
rwx) — set independently per sender, per identity (internal/contacts.CheckPermission). This is the check that's enforced everywhere it applies:internal/mcp/tools.go'sperm.Read/enforceWritePermissiongate reading and replying,internal/daemon/handler.go'sperm.Executegates mission creation. Any number of different people or systems can each hold their own combination; nobody is special by default, and a perfectly verified message from an ungranted sender still unlocks nothing.
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.
- 1mo ago First seen · 98 lines · 2,344 tokens per session scan A 5d4b4d784cd4
beadle CLAUDE.md is an instructions file published in the GitHub repository punt-labs/beadle (3 stars, last pushed today), licensed MIT. It adds 2,344 tokens to every session, about $0.0094 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.