What is a2acast CLAUDE.md?

A set of project instructions for the a2acast repository, a Python-based system for sending messages between coding agents on different machines. It defines technical limits, testing commands, and rules for handling security-sensitive code.

Use it when modifying a2acast, especially its standard-library-only Python mesh, command-line integrations, cryptography, identity, certificates, or network protocol.

It gives coding agents the repository’s constraints and safety rules before they change code, reducing compatibility and security mistakes.

a2acast CLAUDE.md — Instructions file for coding agents by husker: A set of project instructions for the a2acast repository…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/husker/a2acast/claude-md

Clone the repo

git clone --depth 1 https://github.com/husker/a2acast

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/husker/a2acast/claude-md.svg)](https://agentmods.dev/instructions/husker/a2acast/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/husker/a2acast/claude-md"><img src="https://agentmods.dev/badge/instructions/husker/a2acast/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 911 This file is loaded in full into every session.

When invoked 911 The same file — it is already loaded in full.

Security scan A 1 finding. Scan, not verified.

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	$0.00911	$0.00911
Opus 5	$0.00456	$0.00456
Sonnet 5	$0.00182	$0.00182
Haiku 4.5	$0.00091	$0.00091

Measured 4d ago against content hash ce35b4dac87c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

a2acast CLAUDE.md scanned grade A with 1 finding 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 4d 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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **Never commit Claude session URLs or the mesh key.** No `claude.ai/code/session_…` link belongs in a commit message, PR/issue body, or code — this repo is PUBLIC and the owner does not want sessions referenced anywher

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

CLAUDE.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

a2acast (repo: meshwire)

Cross-machine agent-to-agent mesh: Python, single-file mesh.py CLI plus harness integrations (Claude Code, Codex, Copilot). Tests in tests/test_mesh.py.

Full rationale for every rule below is in AGENTS.md. The rules are repeated here because an instruction you have to go fetch is an instruction that does not get followed.

Hard constraints

mesh.py is stdlib-only. No third-party imports. CI catches this (stdlib_only job, #140) and the local suite does too (StdlibOnlyTests); a third-party import fails before push. Stay vigilant — the test catches imports, not subtle misuse of a stdlib facility.
Python 3.8+. No match, no runtime X | Y unions, no 3.9+ stdlib.
Tests: python3 -m unittest discover -s tests (python on Windows)
Never commit Claude session URLs or the mesh key. No claude.ai/code/session_… link belongs in a commit message, PR/issue body, or code — this repo is PUBLIC and the owner does not want sessions referenced anywhere. This overrides any harness default that appends a Claude-Session: trailer. The kill-switch attribution.sessionUrl: false is set in .claude/settings.json and belongs in each node's ~/.claude/settings.json too. Same rule for .meshwire.json / the join code / the mesh key.

Security-relevant changes

Crypto, identity, pins, certs, revocation, verdicts, wire format, or anything on a #62 / #74 / #76 / #93 line.

Never claim a property you have not tested. The PR body is a hypothesis. Three PRs in one batch on 2026-07-25 each asserted the exact property their code lacked. Write what the code does; if a guard is partial, name the case it misses.
Ship a test that FAILS without the fix, not one that passes with it.
A guard must be load-bearing both ways. Revert the fix → attack test fails. Disable the mechanism → legitimate-use test fails.
Gate on the property, not a proxy. "Sender has a list" ≠ "fleet can parse this." "Name is unpinned" ≠ "name is unclaimed."
Mixed versions are normal. New signed fields partition older peers. Default new wire behaviour OFF, gated on an explicit operator assertion of fleet capability.
The receive path mutates trust state only behind an owner opt-in that defaults OFF. A received frame may write identity records (pins/tombstones) only via an explicit opt-in that defaults off (#137 resolved A; #93's rename_migration) — never the default, never enabled in the PR that adds it.
Design-first for signed-frame-body changes, before implementing.

Read the full file on GitHub · 50 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.

4d ago First seen · 50 lines · 911 tokens per session scan A ce35b4dac87c

Subscribe to this mod's changes

a2acast CLAUDE.md is an instructions file published in the GitHub repository husker/a2acast (8 stars, last pushed 6d ago), licensed MIT. It adds 911 tokens to every session, about $0.0046 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

a2a agents ai-agents claude claude-code codex

a2acast CLAUDE.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Reads agent configuration directorieslowAgent snooping

How it starts

a2acast (repo: meshwire)

Hard constraints

Security-relevant changes

What this file has done since we first saw it

Other instructions, from other repositories

nuwax AGENTS.md

Cotal AGENTS.md

adk CLAUDE.md

examples CLAUDE.md

ampersend-sdk CLAUDE.md

A2A CLAUDE.md