Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/zm-bad/headroom/agents-mdgit clone --depth 1 https://github.com/ZM-BAD/headroomWrote 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/zm-bad/headroom/agents-md)<a href="https://agentmods.dev/instructions/zm-bad/headroom/agents-md"><img src="https://agentmods.dev/badge/instructions/zm-bad/headroom/agents-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 | $0.06492 | $0.06492 |
| Opus 5 | $0.03246 | $0.03246 |
| Sonnet 5 | $0.01298 | $0.01298 |
| Haiku 4.5 | $0.00649 | $0.00649 |
Grade A, and why
headroom AGENTS.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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project instructions for AI coding agents (Claude Code, Cursor, Copilot, Windsurf, etc.) working in this repository.
Single source of truth — edit
AGENTS.md, notCLAUDE.md.CLAUDE.mdis a symlink to this file (AGENTS.md). This is deliberate:AGENTS.mdis the cross-agent standard filename (Cursor / Copilot / Windsurf read it), while Claude Code readsCLAUDE.md— the symlink serves both from one source. Most editors and tools (including the Edit tool) reject writing through a symlink ("Refusing to write through symlink"), so always open and editAGENTS.mddirectly. Do not replace the symlink with a real file, delete it, or duplicate the content intoCLAUDE.md.
Project Overview
Headroom is a browser extension built with WXT (next-gen web extension framework). Manifest V3 only — Chrome, Edge, and Firefox. MV2 is not supported (manifestVersion: 3 is set in wxt.config.ts, overriding WXT's Firefox-default MV2).
Commands
npm run dev # Dev + HMR → .output/chrome-mv3-dev/ (DIFFERENT dir from build!)
npm run dev:firefox # Dev mode for Firefox
npm run build # Production build → .output/chrome-mv3/
npm run build:chrome # Same as build (alias)
npm run build:firefox # Production build → .output/firefox-mv3/
npm run build:edge # Production build → .output/edge-mv3/
npm run zip # Package .zip for distribution (Chrome)
npm run zip:firefox # Package .zip for Firefox
npm run zip:edge # Package .zip for Edge
npm run lint # ESLint check
npm run lint:fix # ESLint auto-fix
npm run typecheck # TypeScript type check (tsc --noEmit)
npm test # Run tests in watch mode
npm run test:run # Run tests once (CI + pre-commit)
npx wxt prepare # Regenerate types in .wxt/ (auto-runs on postinstall)
Architecture
WXT uses file-based routing — entrypoints are auto-discovered from entrypoints/ directory.
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 First seen · 224 lines · 6,492 tokens per session scan A c964338a006e
headroom AGENTS.md is an instructions file published in the GitHub repository ZM-BAD/headroom (43 stars, last pushed yesterday), licensed Apache-2.0. It adds 6,492 tokens to every session, about $0.0325 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 2026-08-30.
Other instructions, from other repositories
MaxKB CLAUDE.md
Claude Code instructions for 1Panel-dev/MaxKB, covering claude.md, project overview, development commands, database / static and architecture.
mentedb copilot-instructions.md
Instructions for nambok/mentedb, covering mentedb development instructions, project overview, workspace structure, build, test, and lint and key types.
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
whatsapp-claude-plugin CLAUDE.md
Claude Code instructions for Rich627/whatsapp-claude-plugin, a project described as: Claude Code WhatsApp channel plugin — run AI directly from WhatsApp, voice transcription, remote tool approval, access control. No API keys, no Docker, just a linked device.
plan-forge database.instructions.md
Database patterns for .NET — Dapper/EF Core, parameterized queries, migration strategy.
openclaw-kapso-whatsapp CLAUDE.md
Instructions for Enriquefft/openclaw-kapso-whatsapp, covering claude.md, project, commands, structure and conventions.