Borrowing it
Nothing to install: this file belongs to ng-galien/maket. 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/ng-galien/maket/main/AGENTS.mdgit clone --depth 1 https://github.com/ng-galien/maketWrote 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/ng-galien/maket/agents-md)<a href="https://agentmods.dev/instructions/ng-galien/maket/agents-md"><img src="https://agentmods.dev/badge/instructions/ng-galien/maket/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/ng-galien/maket/agents-md"><img src="https://agentmods.dev/badge/instructions/ng-galien/maket/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 | $0.01896 | $0.01896 |
| Opus 5.5 | $0.00758 | $0.00758 |
| Sonnet 5.5 | $0.00379 | $0.00379 |
| Haiku 4.5 | $0.00190 | $0.00190 |
Grade A, and why
maket 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 16d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maket
Visual design tool for Codex: compose HTML/CSS documents with live preview, manage assets and brand chartes, export PDF, and prepare Gmail drafts. The MCP server uses Streamable HTTP at POST /mcp.
Working contract
- Treat the current checkout and executable contracts as the source of truth. Inspect before changing; preserve unrelated work and persistent data.
- Keep one coherent contract per change. Complete migrations in the same diff: update every entry point, remove the obsolete path, and do not add deprecation shims.
- Persistence types contain persistent state only. Transient state belongs in a dedicated service;
packages/server/src/services/pending.tsis the reference pattern. - Test user-visible workflows at their public boundary. Keep lower-level tests only when they protect a distinct validation, security, wire-format, or deterministic domain contract.
Commands and quality gates
npm run dev # server --watch + Vite HMR; normal development path
npm run dev:watch # server --watch + Vite build --watch into public/
npm run quality # lint + smell review + typecheck + tests + version alignment
npm run lint:fix # Biome autofix
Node >=22. The server must already be running before Codex connects; the human normally owns that process, so do not start a second development server.
Development and simulation runtime
- Use the repository development server for feature simulation and manual verification:
npm run devstarts the checkout server onhttp://localhost:24844(/mcp) and Vite HMR onhttp://localhost:5173. - Port
24843belongs to the installed desktop application. It does not reload checkout changes and MUST NOT be used to validate development changes. - Check the identified development ports before launching. Reuse a suitable running checkout server; when the owner requests a launch, start the documented workflow without replacing or stopping the desktop application.
- Create explicitly named simulation documents and preserve existing development data. Simulate the requested user journey before launching automated suites when the owner asks for that order.
- Automated browser tests use isolated runtimes:
3399and.e2e-maketinplaywright.config.ts, or a per-test random port and temporary directory throughe2e/isolated-test.ts. Never point these suites at development or desktop data.
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.
- 16d ago Changed · +8 lines · +209 tokens per session 4d176dc035c3
- 2mo ago First seen · 90 lines · 1,687 tokens per session scan A c3e865b0cea8
maket AGENTS.md is an instructions file published in the GitHub repository ng-galien/maket (20 stars, last pushed 5d ago), licensed MIT. It adds 1,896 tokens to every session, about $0.0076 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 2026-08-30.
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.