Borrowing it
Nothing to install: this file belongs to hardwood-hq/hardwood. 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/hardwood-hq/hardwood/main/CLAUDE.mdgit clone --depth 1 https://github.com/hardwood-hq/hardwoodWrote 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/hardwood-hq/hardwood/claude-md)<a href="https://agentmods.dev/instructions/hardwood-hq/hardwood/claude-md"><img src="https://agentmods.dev/badge/instructions/hardwood-hq/hardwood/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/hardwood-hq/hardwood/claude-md"><img src="https://agentmods.dev/badge/instructions/hardwood-hq/hardwood/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 | $0.03554 | $0.03554 |
| Opus 5.5 | $0.01422 | $0.01422 |
| Sonnet 5.5 | $0.00711 | $0.00711 |
| Haiku 4.5 | $0.00355 | $0.00355 |
Grade A, and why
hardwood 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
General
Avoid "not my department" thinking; if, for instance, there are build failures you consider unrelated to our current changes, still make an effort to fix them.
When a CLI tool is missing from the dev container (e.g. cmp: command not found), surface it to the user and propose adding the providing package to the Dockerfile's microdnf install list — unless there is an obvious one-line alternative (e.g. command -v for which) or a Python equivalent that is just as terse. Do not silently work around it.
Multiple Sessions
Several Claude sessions may be running against this repository at once. Git allows one HEAD per working tree, so two sessions sharing a checkout also share HEAD, the index and the files: a git checkout in one silently relocates the other, and work gets committed to the wrong branch.
Before committing to a branch, move into your own worktree. Reading needs no worktree — review a PR or a branch from wherever you already are, with gh pr diff, or git fetch and then git log / git diff / git range-diff against FETCH_HEAD. None of those move HEAD. Treat /workspace as a reference checkout that stays on main, since it is where every session lands by default — but that is a default for you to hold to, not a rule to hold against the user. Asked for a branch or a PR in the workspace itself, put it there. Name the worktree directory after its branch, so git worktree list reads as a registry of what is in flight.
Remove your worktree once its work is pushed. Never leave one behind for a review that is over — a list that keeps merged branches and finished reviews is not a registry of anything.
Stage explicit paths. Never git add -A or git commit -a: another session's uncommitted files may be sitting in the tree, and a catch-all stage sweeps them into your commit.
Verify before committing, not after. Check that git rev-parse --abbrev-ref HEAD is the branch you expect and that git status lists only files you touched. A commit on the wrong branch is recoverable through the reflog; one that has been pushed or amended over is not always.
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 Changed · +14 tokens per session 585c748dd581
- 8d ago Changed · +1 lines · +72 tokens per session 606fda98ead5
- 23d ago Changed · +37 tokens per session 3edb1e4a2b88
- 28d ago Changed · +1 lines · +68 tokens per session 91e09db51e82
- 1mo ago Changed · +2 lines · +263 tokens per session 60c30ebd2750
- 1mo ago Changed · +2 lines · +194 tokens per session 6e558bf097ab
- 1mo ago Changed · -2 lines · -98 tokens per session 08b545afad40
- 1mo ago Changed · +1 lines · +124 tokens per session fc7e1cc886ab
- 1mo ago Changed · +3 lines · +273 tokens per session 990183310153
- 1mo ago First seen · 107 lines · 2,607 tokens per session scan A 4bb0d28dc345
hardwood CLAUDE.md is an instructions file published in the GitHub repository hardwood-hq/hardwood (417 stars, last pushed 4d ago), licensed Apache-2.0. It adds 3,554 tokens to every session, about $0.0142 per session on Opus 5.5. 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 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.