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.
npx agentmods add instructions/lifeanalysis/company-mesh/agents-mdgit clone --depth 1 https://github.com/LifeAnalysis/company-meshWrote 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/lifeanalysis/company-mesh/agents-md)<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>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 | $0.00177 | $0.00177 |
| Opus 5 | $0.00088 | $0.00088 |
| Sonnet 5 | $0.00035 | $0.00035 |
| Haiku 4.5 | $0.00018 | $0.00018 |
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.
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 --workspaceandnpm test --workspace packages/company-mcpbefore 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.
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.
- 3d ago First seen · 12 lines · 177 tokens per session scan A ab56c1d29ab6
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.
Other instructions, from other repositories
rayfish CLAUDE.md
Claude Code instructions for rayfish/rayfish, covering rayfish, build & test, never, conventions and git.
tweazy CLAUDE.md
Claude Code instructions for aaronjmars/tweazy, covering claude.md, development commands, project architecture, core systems and api routes structure.
osvauld AGENTS.md
Instructions for osvauld/osvauld, covering osvauld, offline-first principle, mandatory subagent delegation, delegation map and crate boundaries.
osvauld CLAUDE.md
Instructions for osvauld/osvauld, covering osvauld code policies, logging policy, comment policy, code structure and crate boundaries.
ohloss CLAUDE.md
Claude Code instructions for kalepail/ohloss, covering claude.md, project overview, key technologies, dependency management and current core dependencies.
ohloss AGENTS.md
AGENTS.md instructions for kalepail/ohloss, covering agents.md - available tooling reference, quick start, dependency management, current core dependencies and before adding dependencies.