mesh CLAUDE.md

mesh CLAUDE.md is an instructions file for coding agents from ycanerden/mesh. It costs 1,167 tokens per session, scanned A, original, MIT.

Repository instructions for Mesh, a company project organized around AI agents building and operating software. They describe the mission, leadership roles, deployment authority, and recurring executive updates.

In plain words
What is it for?
Use them when contributing to the Mesh project, preparing executive check-ins, deciding who may deploy, or documenting work that needs an owner's approval.
Why use it?
They clarify who makes which decisions and how the team reports progress, blockers, and requests. This reduces confusion about ownership and deployment responsibilities.

Instructions file

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/ycanerden/mesh/claude-md
Clone the repo
git clone --depth 1 https://github.com/ycanerden/mesh

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 mesh CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ycanerden/mesh/claude-md.svg)](https://agentmods.dev/instructions/ycanerden/mesh/claude-md)
Your own site
<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>
Per session 1,167 This file is loaded in full into every session.
When invoked 1,167 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 $0.01167 $0.01167
Opus 5 $0.00583 $0.00583
Sonnet 5 $0.00233 $0.00233
Haiku 4.5 $0.00117 $0.00117

Measured 5d ago against content hash 4a896de9a86d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

CLAUDE.md · 118 lines

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.

Read the full file on GitHub · 118 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.

  1. 5d ago First seen · 118 lines · 1,167 tokens per session scan A 4a896de9a86d

Subscribe to this mod's changes

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.