Borrowing it
Nothing to install: this file belongs to sunglasses-dev/sunglasses. 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/sunglasses-dev/sunglasses/main/AGENTS.mdgit clone --depth 1 https://github.com/sunglasses-dev/sunglassesWrote 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/sunglasses-dev/sunglasses/agents-md)<a href="https://agentmods.dev/instructions/sunglasses-dev/sunglasses/agents-md"><img src="https://agentmods.dev/badge/instructions/sunglasses-dev/sunglasses/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/sunglasses-dev/sunglasses/agents-md"><img src="https://agentmods.dev/badge/instructions/sunglasses-dev/sunglasses/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 | $0.01149 | $0.01149 |
| Opus 5 | $0.00575 | $0.00575 |
| Sonnet 5 | $0.00230 | $0.00230 |
| Haiku 4.5 | $0.00115 | $0.00115 |
Grade A, and why
sunglasses 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 yesterday.
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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — working in this repo as an AI agent
For coding agents (Claude Code, Codex, Cursor, Aider, or a human who wants the short version). Everything here is checkable against the repo; if a line stops being true, fix the line.
What this project is, in one paragraph
Sunglasses inspects content before an AI agent acts on it, and reports what it found and what it could not read. The whole value is that second half. A tool that says "clean" about a file it never opened is worse than no tool, because someone will trust it. Every change you make here is judged against that.
Run the tests
python3 -m pytest -q # from the repo root, with NO path argument
pytest.ini pins testpaths on purpose. On 2026-08-28 two honest reviewers
measured 780 and 778 passing on the same commit, because two root-level tests
only collect when pytest runs from root scope. Passing an explicit path
re-creates that ambiguity — a bare run from the root is the only measurement
anyone should quote.
It still reproduces. Try it:
$ python3 -m pytest -q --collect-only # 1397 tests collected
$ python3 -m pytest -q --collect-only tests # 1395 tests collected
Two tests, same commit, different answer — decided entirely by an argument you did or did not type.
What CI actually runs
.github/workflows/pattern-integrity.yml, on six Python versions —
3.9, 3.10, 3.11, 3.12, 3.13, 3.14 — all fully blocking, none informational.
It installs real native decoders (tesseract-ocr, libzbar0, ffmpeg) and
pins Pillow (12.3.0; 3.9 necessarily takes 11.3.0). That is not incidental: a
missing decoder turns a real finding into silence, so a green run without them
proves nothing about media scanning. If you touch image, QR, PDF or audio paths,
assume the decoder version matters until you have shown it does not.
The truth layer — do not hand-edit published numbers
stats/current.json is the single source for every published figure: pattern
count, category count, keyword count, language count, version. README stats,
site JSON-LD and package metadata are generated from 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.
- yesterday First seen · 102 lines · 1,149 tokens per session scan A 4da9da52c06d
sunglasses AGENTS.md is an instructions file published in the GitHub repository sunglasses-dev/sunglasses (5 stars, last pushed today), licensed MIT. It adds 1,149 tokens to every session, about $0.0057 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 2026-09-11.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).