Borrowing it
Nothing to install: this file belongs to dougstanford/living-manual. 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/dougstanford/living-manual/main/CLAUDE.mdgit clone --depth 1 https://github.com/dougstanford/living-manualWrote 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/dougstanford/living-manual/claude-md)<a href="https://agentmods.dev/instructions/dougstanford/living-manual/claude-md"><img src="https://agentmods.dev/badge/instructions/dougstanford/living-manual/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/dougstanford/living-manual/claude-md"><img src="https://agentmods.dev/badge/instructions/dougstanford/living-manual/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01108 | $0.01108 |
| Opus 5 | $0.00554 | $0.00554 |
| Sonnet 5 | $0.00222 | $0.00222 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
living-manual 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 10d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
living-manual
This repo is the living-manual plugin itself. The manual below documents the plugin, built by the plugin: dogfooding is the point. Changes to skills/, scripts/, templates/, or reference/ are user-facing.
Start of every session
git fetch origin, then create your working branch fromorigin/main:git switch -c <topic> origin/main. Ticket work readsticket-NNNN-<slug>. Use agit worktreeif another session may be active. Never build directly onmain.- Read
README.mdanddocs/WORKFLOW.mdbefore your first commit.
If the working tree has uncommitted non-trivial changes, or the session was deliberately started on another branch, surface that instead of forcing a switch.
How work lands — non-negotiable
main is protected: direct pushes, force-pushes, and deletion are
refused by GitHub itself. Everything reaches trunk through a merge
request that passes Manual reflects the code.
- One branch = one session = one concern. If a branch grows a second concern, split it.
- Never
git add -Aorgit add .in a tree another session may share — stage explicit paths. - Push the branch the same day it exists; open the MR with
gh pr create --base main. - Rebase onto trunk when you want a clean history; you no longer need to, since branches merge in any order without conflicting on the manual.
- Merge with any method — merge commit, squash, or rebase. The manual
records a content hash per user-facing surface, not a commit sha, so no
merge method can orphan it (this reversed the old merge-commit-only
rule; see TICKET-0006 and
docs/WORKFLOW.md§3). - Required approvals are 0 by design (agent sessions act as the owner, and GitHub forbids self-approval), so the enforced gate is MR + green check. The merge click is the human judgment.
- Write the MR body in plain, user-facing language: what changed, why, and what to look at. The reviewer may not read the diff.
Full contract, including the protection ruleset and the reviewer's
guide: docs/WORKFLOW.md.
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.
- 10d ago First seen · 93 lines · 1,108 tokens per session scan A 19d3878a0151
living-manual CLAUDE.md is an instructions file published in the GitHub repository dougstanford/living-manual (3 stars, last pushed 28d ago), licensed MIT. It adds 1,108 tokens to every session, about $0.0055 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).
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.
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.