Borrowing it
Nothing to install: this file belongs to gabrieldabbah/genesis. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gabrieldabbah/genesis/main/CLAUDE.mdgit clone --depth 1 https://github.com/gabrieldabbah/genesisWrote 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/gabrieldabbah/genesis/claude-md)<a href="https://agentmods.dev/instructions/gabrieldabbah/genesis/claude-md"><img src="https://agentmods.dev/badge/instructions/gabrieldabbah/genesis/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 5.1 | $0.03437 | $0.03437 |
| Opus 5 | $0.01718 | $0.01718 |
| Sonnet 5 | $0.00687 | $0.00687 |
| Haiku 4.5 | $0.00344 | $0.00344 |
Grade A, and why
genesis 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 6d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Genesis
What this is: the source of a Claude Code plugin — skills, hooks and templates that scaffold new projects and bring existing ones up to standard. Instructions in English, not application code; there is no build and no test suite, only the gate below. Who is exposed: anyone who installs it. Everything here runs on other people's machines and writes files into other people's repositories.
Environment
There is no database, no deploy target, no queue and no bucket. CI is one workflow
(.github/workflows/gate.yml) running scripts/gate.sh on pull
requests and pushes to dev/main; it reads the repository and nothing else, needs no secret, and has no
deploy step. No credential is needed to work on this repo, it contains no .env, and nothing in it opens a socket or
makes a network call. The complete list of what it touches:
- GitHub.
originishttps://github.com/gabrieldabbah/genesis.git, public (fromgit remote -v). Branches aredevandmainonly; PRs go fromdevtomain(skills/generate-pr/SKILL.md). Reached withgit/ghfrom a dev machine. - Provider domains are data, not connections. Every service endpoint named in this repo
(
api.stripe.com,*.supabase.co, …) lives in integrations/registry/*.yaml as instructions for a future scaffolded project. Nothing in this repo dials them, and the registry files carry env-key names only, never values. - Two Stop hooks, both currently inert. .claude/settings.json registers
todo-archive-reminder.mjs for sessions in this repo — it exits
silently because the repo has no
TODO.md/archive pair for it to find — and deniesReadon.env*,secrets/,*.key,*.pem,~/.ssh,~/.awsand other credential stores. hooks/hooks.json registers stop-acceptance.mjs on machines that install the plugin; it exits immediately unless.scratch/acceptance.jsonexists, which only a running genesis build writes. - templates/env/ ships
.env.example,.env.developmentand.env.productiontracked on purpose (.gitignore un-ignores them). Every value in all three is empty; they are placeholder templates. .claude/is personal except two paths. .gitignore ignores.claude/*but tracks.claude/hooks/and.claude/settings.jsonso working on genesis dogfoods what it ships..claude/skills/(localgenerate-prandgit-commithelpers) stays on this machine and is not shipped.
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.
- 6d ago First seen · 193 lines · 3,437 tokens per session scan A e484a2651307
genesis CLAUDE.md is an instructions file published in the GitHub repository gabrieldabbah/genesis (4 stars, last pushed 1mo ago), licensed MIT. It adds 3,437 tokens to every session, about $0.0172 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.