Borrowing it
Nothing to install: this file belongs to meganemura/headsign. 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/meganemura/headsign/main/AGENTS.mdgit clone --depth 1 https://github.com/meganemura/headsignWrote 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/meganemura/headsign/agents-md)<a href="https://agentmods.dev/instructions/meganemura/headsign/agents-md"><img src="https://agentmods.dev/badge/instructions/meganemura/headsign/agents-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/meganemura/headsign/agents-md"><img src="https://agentmods.dev/badge/instructions/meganemura/headsign/agents-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 | $0.00585 | $0.00585 |
| Opus 5.5 | $0.00234 | $0.00234 |
| Sonnet 5.5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
headsign 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 27d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Changing headsign
These instructions govern headsign itself. Consumer projects keep their own goals, constraints, and commands.
For incoming feedback or changes to headsign's skills, use the project-local improve-headsign skill. Its responsibilities guide judgment; adapt the method to the evidence and task authority.
Before changing skills, packaging, or product guidance, read ADR-0039, ADR-0043, and ADR-0044. Use the ADR index for historical reasons.
Carry these principles into each change:
- Give the model objectives, constraints, facts, and authority to choose a method.
- Require method assessment during work when evidence exposes a weakness, and at completion.
- Apply useful repairs to the current work and verify affected results.
- Choose consequential improvements; retaining a useful method is valid.
- Preserve requested outcomes, explicit budgets, independent review, and the user's ability to stop.
- Keep skills small. Explain any added instruction and consider what better models let us remove.
- State future assumptions and uncertainty separately from observed behavior.
headsign distributes two plain skill directories under skills/:
create-project-skill and improve-project-skill.
Do not restore plugin packaging, a CLI, workflow state, hooks, or npm publishing
as a routine repair. A design change to this boundary requires an explicit
amendment to ADR-0044 and the user's authority.
Follow Maintenance. Run the contributor check with Node 24:
node scripts/check.ts
Read the changed skills and required references as one set. For behavioral changes, exercise relevant scenarios and report what the check cannot establish. Check current guides for instructions that conflict with the new behavior. Keep the English and Japanese guides aligned.
When delegating, include relevant ADR paths, ownership, and task constraints. Ask reviewers to check policy alignment and observable behavior.
Before handover, explain design alignment and the behavior verified. A routine fix needs a short explanation. If an accepted decision changes, amend it explicitly instead of overriding it in a skill.
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.
- 27d ago Changed · +4 lines · +51 tokens per session 7cf96d52e0ad
- 29d ago Changed · -10 lines · -263 tokens per session 2d51a6d68511
- 1mo ago Changed · +26 lines · +352 tokens per session b075df532acd
- 1mo ago First seen · 41 lines · 445 tokens per session scan A 0419ceb0b435
headsign AGENTS.md is an instructions file published in the GitHub repository meganemura/headsign (1 stars, last pushed 28d ago), licensed MIT. It adds 585 tokens to every session, about $0.0023 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 2026-09-13.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.