Borrowing it
Nothing to install: this file belongs to wasulajr/headsup. 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/wasulajr/headsup/main/CLAUDE.mdgit clone --depth 1 https://github.com/wasulajr/headsupWrote 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/wasulajr/headsup/claude-md)<a href="https://agentmods.dev/instructions/wasulajr/headsup/claude-md"><img src="https://agentmods.dev/badge/instructions/wasulajr/headsup/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/wasulajr/headsup/claude-md"><img src="https://agentmods.dev/badge/instructions/wasulajr/headsup/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 | $0.00658 | $0.00658 |
| Opus 5.5 | $0.00263 | $0.00263 |
| Sonnet 5.5 | $0.00132 | $0.00132 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
headsup 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 2mo 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
headsup: instructions for Claude sessions working in this repo
Releases are mandatory (issue #19)
Any push to main that changes behavior (features, fixes, skills, hooks, scripts, setup) MUST go through the release script. Never push release-worthy commits bare.
scripts/release.sh <major|minor|patch> -m "what changed" [-m "more" ...]
The script bumps VERSION, prepends a CHANGELOG.md section, commits, tags vX.Y.Z, and pushes main with tags. It refuses to run on a dirty tree or off main, so land your feature commits first, then cut the release.
Semver convention:
- PATCH: bug fixes, doc corrections that affect usage
- MINOR: new features, new skills, new hooks
- MAJOR: breaking conf or layout changes that require re-running
setup.sh
Pure typo/comment-only pushes may skip a release, but say so explicitly in the conversation when skipping.
Bootstrap files
VERSION at the repo root is the installed-version source of truth for scripts; git describe --tags is the fallback for dev checkouts between releases.
Authoring skills (SKILL.md frontmatter)
Every skill's SKILL.md opens with a YAML frontmatter block (name, description). Skill loaders (Claude Code, Codex, and the ~/.agents/skills scanner) parse that YAML and silently skip any skill whose frontmatter fails to parse: there is no error, the skill simply never appears in the menu. Debugging this from the symptom ("my skill is missing") is painful because the file is right there on disk, so prevent it at authoring time.
The most common break is an unquoted colon in the description. In YAML a plain (unquoted) scalar cannot contain ": " (a colon followed by a space): the parser reads it as the start of a nested mapping and throws mapping values are not allowed in this context. This line is invalid, so the skill vanishes:
description: Change colors for Codex sessions: idle, working, and waiting.
Rule: if a frontmatter value contains a colon, or starts with a character YAML treats specially ([ { # & * ! | > % @ or a backtick), wrap the whole value in double quotes. Quoting is always safe, so when in doubt, quote it:
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.
- 2mo ago First seen · 48 lines · 658 tokens per session scan A e376afb298cf
headsup CLAUDE.md is an instructions file published in the GitHub repository wasulajr/headsup (1 stars, last pushed 3d ago), licensed MIT. It adds 658 tokens to every session, about $0.0026 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 2026-08-31.
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.