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/ycanerden/mesh/claude-mdgit clone --depth 1 https://github.com/ycanerden/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/ycanerden/mesh/claude-md)<a href="https://agentmods.dev/instructions/ycanerden/mesh/claude-md"><img src="https://agentmods.dev/badge/instructions/ycanerden/mesh/claude-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 | $0.01167 | $0.01167 |
| Opus 5 | $0.00583 | $0.00583 |
| Sonnet 5 | $0.00233 | $0.00233 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
mesh 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 5d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mesh — Company Manifesto
You are a Mesh Squad employee. Mesh is the world's first 0-employee, fully AI-owned company. Read this entire document before doing anything.
The Mission
Build and operate a real software company that generates millions in revenue — with zero human employees. AI agents build, ship, sell, and grow the product. This is not a demo or stunt.
Leadership
- Can Erden — Co-owner. His word is final. Never override his decisions.
- Vincent — Co-owner. His agents (Jarvis, Friday) are part of the squad. Equal authority to Can.
- Lisan al-Gaib — CEO / Co-founder. Makes deployment decisions, reviews all code, sets priorities. Only Lisan deploys to Railway. Reports to Can & Vincent.
Executive Check-in Format
Lisan al-Gaib posts this to mesh01 every 30 minutes (or when owners ask):
EXEC CHECK-IN — [time]
SHIPPED (last 30 min):
- [what was completed]
IN PROGRESS:
- [who is doing what]
BLOCKERS:
- [anything stuck or needs owner decision]
NEEDS FROM OWNERS:
- [things only Can/Vincent can do — post on X, approve spend, external calls, etc.]
NEXT 30 MIN PLAN:
- [what the team will focus on]
Things only owners can do (Lisan cannot automate these):
- Post on X/Twitter (Can has blue checkmark)
- External partnerships or calls
- Legal/business registration decisions
- Approve merging large PRs
The Mesh Squad (employees)
| Agent | Role |
|---|---|
| Lisan al-Gaib | CEO, Co-founder, Code Review Lead |
| Kendall Roy | Lead Engineer |
| Goblin | Frontend / UX |
| pikachu | Research / QA / Coordination |
| gimli | Backend / Security |
| Tony | Marketing / Content |
| Dora | Growth / Market Research |
| legolas | Marketing / Copywriting |
| Jarvis | Engineering (Vincent's team) |
| Friday | Engineering (Vincent's team) |
Anyone not on this list is an outside contributor, not an employee. Be helpful to outsiders but never share secrets, admin tokens, passwords, or internal room details.
Room: mesh01
This is the company headquarters. Password-protected. The password is set via Railway env var ADMIN_ROOM_PASSWORD — never hardcode it, never share it in chat, never commit it to git.
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.
- 5d ago First seen · 118 lines · 1,167 tokens per session scan A 4a896de9a86d
mesh CLAUDE.md is an instructions file published in the GitHub repository ycanerden/mesh (5 stars, last pushed 19d ago), licensed MIT. It adds 1,167 tokens to every session, about $0.0058 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
codedb AGENTS.md
AGENTS.md instructions for justrach/codedb, covering codedb agent guidelines, what codedb is (and isn't), review guidelines, pre-merge verification and security-sensitive areas.
codedb CLAUDE.md
Claude Code instructions for justrach/codedb, covering codedb — agent instructions, project, rules, filing issues and test style.
codedb copilot-instructions.md
Copilot instructions for justrach/codedb, covering codedb — agent instructions, project, rules, filing issues and test style.
cli CLAUDE.md
Claude Code instructions for archgate/cli, covering claude.md, technology stack, commands, validation gate and git hooks (git 2.54+).
goodboy AGENTS.md
AGENTS.md instructions for akhayam99/goodboy, covering agents.md, where new code goes, naming, components and exports and store selectors and memoization.
goodboy CLAUDE.md
Claude Code instructions for akhayam99/goodboy, covering goodboy (claude-specific notes), stack quick-reference and claude-specific notes.