Borrowing it
Nothing to install: this file belongs to LamantinAI/mayak. 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/LamantinAI/mayak/main/AGENTS.mdgit clone --depth 1 https://github.com/LamantinAI/mayakWrote 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/lamantinai/mayak/agents-md)<a href="https://agentmods.dev/instructions/lamantinai/mayak/agents-md"><img src="https://agentmods.dev/badge/instructions/lamantinai/mayak/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/lamantinai/mayak/agents-md"><img src="https://agentmods.dev/badge/instructions/lamantinai/mayak/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 | $0.02162 | $0.02162 |
| Opus 5.5 | $0.00865 | $0.00865 |
| Sonnet 5.5 | $0.00432 | $0.00432 |
| Haiku 4.5 | $0.00216 | $0.00216 |
Grade A, and why
mayak 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 21d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- mayak CLAUDE.md — 100% identical, 83 lines differ
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
The shared Mayak agent rules — the one rendered contract. Codex reads this file directly;
Claude Code reads it through CLAUDE.md, which imports it, because Claude Code does
not read AGENTS.md itself.
Generated from docs/agent_rules.md via scripts/sync_agent_docs.py. Do not edit this file manually.
Quick Start
- Copy the
reference_taskvertical. It is the one worked example and it exists to be copied — twelve files plus three wiring edits;.agents/skills/add-verticalcarries the order and the removal list for when your own vertical replaces it. A project that has replaced it edits this line and nothing else: the wrapper's Quick Start is generated from these bullets. - If
.envis missing:make init-project. Nothing else creates it, and the app does not start without it. Idempotent — it never overwrites an existing.env. make gate-fastwhile editing — format, lint, types with the tests, layer rules, in seconds.make quality-gatesbefore committing — its test run includes the db tier, which runs your queries and migrations against a PostgreSQL it starts itself (needs Docker). When the diff touched endpoints, wiring or a migration,make test-e2etoo: only it runs the built image over HTTP.
Running the service needs one more decision: the shipped .env points at PostgreSQL with
placeholder credentials, so make run-local fails until either a database is up
(docker compose -f docker-compose.yml -f docker-compose.postgres.yml up -d db) or the
project declares it needs none (POSTGRES_ENABLED=false in .env).
Run make help for the full grouped command list — it reads the Makefile directly.
Task Process
- When the same cause fails a third time — the same error, whatever flags or command you changed around it — stop editing: write down the assumption you now doubt; if a gate named a rule ID, ask
uv run python scripts/doctor_ai_context.py --rule <rule_id>for its playbook and read only the files it names; change one thing before rerunning. - Never claim task completion without fresh
make quality-gatesevidence. - Use a fresh subagent for independent verification — do not self-verify.
- A finished task ends as an open pull request, never a merge: branch
task/<ID>→ commit → push →gh pr create --base main. No deploy job ships — "done" means open and green. - A fixed defect is proved by one test in the same pull request, failing on the defective code for the stated reason and passing once fixed — not by a test, an ADR, and a wrapper bullet all at once. A new blocking validator rule ships with one failing example and several correct ones it must pass — earned by a real defect, not symmetry.
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.
- 21d ago Changed · +59 tokens per session 0f8c98b780db
- 27d ago Changed · -2 lines · +109 tokens per session a365858732fa
- 1mo ago Changed · -54 lines · -3,331 tokens per session 575805a5d5b3
- 1mo ago Changed · +5 lines · +831 tokens per session 6040d17f9415
- 1mo ago Changed · +2 lines · +38 tokens per session 5926058eed1b
- 1mo ago Changed · +218 tokens per session d3774bcfed9d
- 1mo ago Changed · +106 tokens per session 7c73cef73366
- 1mo ago First seen · 128 lines · 4,132 tokens per session scan A df32f6f99652
mayak AGENTS.md is an instructions file published in the GitHub repository LamantinAI/mayak (5 stars, last pushed 21d ago), licensed MIT. It adds 2,162 tokens to every session, about $0.0086 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 2026-08-31.
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.