Borrowing it
Nothing to install: this file belongs to gglucass/headroom-desktop. 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/gglucass/headroom-desktop/main/CLAUDE.mdgit clone --depth 1 https://github.com/gglucass/headroom-desktopWrote 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/gglucass/headroom-desktop/claude-md)<a href="https://agentmods.dev/instructions/gglucass/headroom-desktop/claude-md"><img src="https://agentmods.dev/badge/instructions/gglucass/headroom-desktop/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/gglucass/headroom-desktop/claude-md"><img src="https://agentmods.dev/badge/instructions/gglucass/headroom-desktop/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 | $0.03139 | $0.03139 |
| Opus 5.5 | $0.01256 | $0.01256 |
| Sonnet 5.5 | $0.00628 | $0.00628 |
| Haiku 4.5 | $0.00314 | $0.00314 |
Grade A, and why
headroom-desktop 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 4d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - headroom-desktop
This file holds only what the model cannot derive: project invariants, environment
quirks, and concrete commands. Generic coding-style coaching (write simply, read
before editing, state the bug and stop) was removed on 2026-08-03 — modern models do
it unprompted and the harness enforces the rest. Do not re-add it.
Every line here is re-sent with every request. A rule set needed for only one kind of task goes in
docs/ with a one-line pointer here that says when to read it (see Wheel Bump Rules).
Testing Rules
- After any code change, run the relevant tests/checks before declaring the task done. Do not ask the user to verify.
- Rust changes:
cargo test --manifest-path src-tauri/Cargo.toml --lib <filter>for the affected module, pluscargo check --manifest-path src-tauri/Cargo.tomlif the change crosses module boundaries. - Full Rust suite, once per change set (never between edits):
cargo test --manifest-path src-tauri/Cargo.toml --lib -- --skip against_the_installed_wheel(~48s). No lock: two of these at once took 52s against 49s for one, while queueing them made the second wait 95s (2026-10-16). - The 24
*_against_the_installed_wheeltests boot the installed Python runtime: ~40s (2026-10-19), ~90% of the suite's CPU and a 1.2 GB peak. Run them when a change touchesSITECUSTOMIZE_PY, the wheel pin orsrc-tauri/python/*.lock, queued on the lock the release-train gates take:lockf -k -t 900 /tmp/headroom-cargo.lock cargo test --manifest-path src-tauri/Cargo.toml --lib against_the_installed_wheel(give the Bash call a long timeout). CI's wheel job and the release-train gates run them on every push and rc. - After a failure, re-run only the failing tests until they pass, then the full-suite command once. Never re-run the whole suite to retry a failure.
- Frontend changes:
npx tsc --noEmitand any relevant Vitest suite. For visual changes, see Styling Rules. - If a test cannot be run in this environment, say so explicitly rather than skipping silently.
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.
- 4d ago Changed · +35 tokens per session 134da2bcd680
- 7d ago Changed · -9 lines · -8,277 tokens per session 86582d340479
- 8d ago Changed · +403 tokens per session adf355975361
- 9d ago Changed · -1 lines · -46 tokens per session 78792a3099f6
- 10d ago Changed · +3 lines · +1,073 tokens per session 6bac69514cac
- 14d ago Changed · +498 tokens per session c87ac7e9fb3d
- 15d ago Changed · +229 tokens per session 955a0296c31e
- 18d ago Changed · +601 tokens per session 6027d1ccfab6
- 20d ago Changed · +60 tokens per session f84d7712e1c2
- 22d ago First seen · 66 lines · 8,563 tokens per session scan A 1e139f90cb18
headroom-desktop CLAUDE.md is an instructions file published in the GitHub repository gglucass/headroom-desktop (625 stars, last pushed today), licensed MIT. It adds 3,139 tokens to every session, about $0.0126 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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.