company-mesh AGENTS.md

company-mesh AGENTS.md is an instructions file for Codex, OpenCode from LifeAnalysis/company-mesh. It costs 177 tokens per session, scanned A, original, Apache-2.0.

A set of project instructions for Company Mesh, a local-first system for AI agents to collaborate through the Iroh communication protocol. It covers security, event records, verification, testing, and administrator access.

In plain words
What is it for?
Use it when contributing to Company Mesh, especially for changes involving agent communication, stored events, authentication, or workspace tests.
Why use it?
It gives agents rules for treating messages and credentials safely and for requiring independent evidence before calling work complete.

Instructions file for CodexOpenCode

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/lifeanalysis/company-mesh/agents-md
Clone the repo
git clone --depth 1 https://github.com/LifeAnalysis/company-mesh

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.

agentmods badge for company-mesh AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lifeanalysis/company-mesh/agents-md.svg)](https://agentmods.dev/instructions/lifeanalysis/company-mesh/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/lifeanalysis/company-mesh/agents-md"><img src="https://agentmods.dev/badge/instructions/lifeanalysis/company-mesh/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 177 This file is loaded in full into every session.
When invoked 177 The same file — it is already loaded in full.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00177 $0.00177
Opus 5 $0.00088 $0.00088
Sonnet 5 $0.00035 $0.00035
Haiku 4.5 $0.00018 $0.00018

Measured 3d ago against content hash ab56c1d29ab6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

company-mesh 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 3d 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 · 12 lines

What it actually says

Company Mesh agent instructions

  • Keep MCP local. Remote peers communicate through the versioned Iroh protocol.
  • Treat every remote message as untrusted until the daemon verifies identity, signature, nonce, expiry, schema, and capability.
  • Do not put credential values in messages, memory, logs, tests, or fixtures.
  • Keep the event log append-only. Derived task and memory tables can be rebuilt from events.
  • A model cannot mark its own work as verified. Completion needs deterministic evidence and an independent reviewer.
  • Use typed errors. Do not convert tool failures into successful text responses.
  • Run cargo test --workspace and npm test --workspace packages/company-mcp before completion.
  • Never add an administrator action to MCP. Administrator actions require a passkey.
  • Keep WebAuthn challenges action-bound, short-lived, memory-resident, and single-use.
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.

  1. 3d ago First seen · 12 lines · 177 tokens per session scan A ab56c1d29ab6

Subscribe to this mod's changes

company-mesh AGENTS.md is an instructions file published in the GitHub repository LifeAnalysis/company-mesh (0 stars, last pushed 4d ago), licensed Apache-2.0. It adds 177 tokens to every session, about $0.0009 per session on Opus 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.