Borrowing it
Nothing to install: this file belongs to VasilisPlavos/Cookie-AutoDeleteV3. 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/VasilisPlavos/Cookie-AutoDeleteV3/main/AGENTS.mdgit clone --depth 1 https://github.com/VasilisPlavos/Cookie-AutoDeleteV3Wrote 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/vasilisplavos/cookie-autodeletev3/agents-md)<a href="https://agentmods.dev/instructions/vasilisplavos/cookie-autodeletev3/agents-md"><img src="https://agentmods.dev/badge/instructions/vasilisplavos/cookie-autodeletev3/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/vasilisplavos/cookie-autodeletev3/agents-md"><img src="https://agentmods.dev/badge/instructions/vasilisplavos/cookie-autodeletev3/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 | $0.01827 | $0.01827 |
| Opus 5.5 | $0.00731 | $0.00731 |
| Sonnet 5.5 | $0.00365 | $0.00365 |
| Haiku 4.5 | $0.00183 | $0.00183 |
Grade A, and why
Cookie-AutoDeleteV3 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 2d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for any AI agent working in this repository.
What this is
Cookie AutoDelete V3 — a Manifest V3 browser extension (TypeScript + React + Redux) that auto-deletes unwanted cookies and other site data. It's a MV3 fork of the original Cookie AutoDelete. Ships one codebase to both Chromium (Chrome / Edge / Brave / Vivaldi) and Firefox; the two differ only by a manifest patch at build time.
Working agreements
- Never push to
main. Work on a branch and open a PR.mainis protected and a push to it auto-publishes a release (see Release process). - Every PR updates the release notes. Add/extend an entry in
src/ui/settings/ReleaseNotes.jsonunder the version this PR ships in. That file feeds the "What's New" Welcome tab users see after an update. - Code is self-explaining. Prefer clear names over comments. Add a comment only
when the why is non-obvious (e.g. an MV3 service-worker quirk, a
cross-browser workaround) — the existing comments in
src/background/are the bar to match, not to exceed. - Run
npm run test-all(tests + lint) before opening a PR. Lint is zero-warnings.
Commands
npm run compile # webpack production build -> extension/bundles/
npm run dev # webpack --watch (rebuild on change)
npm run build # compile + package BOTH Chrome & Firefox into builds/
npm run build:chrome # package Chromium only (optional version bump, see below)
npm run build:firefox # package Firefox only
npm run lint # eslint, --max-warnings 0
npm test # jest
npm run test-all # test + lint (run before every PR)
npm run test:coverage # jest with coverage
npm run test:e2e # Playwright harness in a real Chromium (local only, needs network)
Run a single test file / name:
npx jest __tests__/tools/resolveBuildVersion.test.js
npx jest -t "partitioned"
Version bump (writes both package.json and extension/manifest.json):
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.
- 2d ago Changed · +2 tokens per session d09ce3115db2
- 18d ago First seen · 160 lines · 1,825 tokens per session scan A 9bb30641dd12
Cookie-AutoDeleteV3 AGENTS.md is an instructions file published in the GitHub repository VasilisPlavos/Cookie-AutoDeleteV3 (35 stars, last pushed 3d ago), licensed MIT. It adds 1,827 tokens to every session, about $0.0073 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 2026-10-02.
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.