Borrowing it
Nothing to install: this file belongs to mnzralee/claude-multi-agent-architecture. 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/mnzralee/claude-multi-agent-architecture/main/AGENTS.mdgit clone --depth 1 https://github.com/mnzralee/claude-multi-agent-architectureWrote 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/mnzralee/claude-multi-agent-architecture/agents-md)<a href="https://agentmods.dev/instructions/mnzralee/claude-multi-agent-architecture/agents-md"><img src="https://agentmods.dev/badge/instructions/mnzralee/claude-multi-agent-architecture/agents-md.svg" alt="Measured on agentmods" 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 | $0.01259 | $0.01259 |
| Opus 5 | $0.00629 | $0.00629 |
| Sonnet 5 | $0.00252 | $0.00252 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
claude-multi-agent-architecture 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 8d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Cross-Tool Agent Configuration
Tool-agnostic context for AI coding assistants (Claude Code, Cursor, Codex, Gemini, Amp, and others). For Claude Code specifics, see
CLAUDE.mdand the.claude/directory. Replace every[CUSTOMIZE]placeholder with your project's values.
Project Overview
[PROJECT_NAME] is a [DESCRIPTION].
- Backend: [FRAMEWORK] with [ARCHITECTURE_PATTERN]
- Frontend: [FRAMEWORK]
- Database: [DATABASE] with [ORM]
- Infrastructure: [INFRA_PLATFORM]
- Repository: [monorepo | polyrepo]
Conventions
Code style (illustrative defaults; adapt to your stack)
- TypeScript strict mode; no
any(useunknownplus type guards). - Typed domain errors; never swallow exceptions or use silent fallbacks.
- No
@ts-ignore/@ts-expect-error.
Git
- Conventional commits:
type(scope): subject(feat, fix, refactor, chore, docs, test, perf, security). - File-by-file staging; commit each logical unit. No AI attribution, no emojis.
Testing
- Testing pyramid: roughly 70% unit, 20% integration, 10% end-to-end. Prove results with real output.
Architecture
- Clean architecture: domain to application to infrastructure to interface. Dependencies point inward (domain has zero external deps). Repository pattern for data access; use cases for business logic.
Orchestration model
- Decide before orchestrating. Prefer a single prompt or a fixed workflow over an autonomous swarm. Pick the smallest pattern that fits.
- Single writer, many readers. Parallel agents may read/analyze/review; exactly one agent mutates files or commits at a time.
- Prove with artifacts. "Done" means a commit SHA, test output, or a passing check, not a narration.
Operating standard (doctrine, every model tier)
Every model, whatever its capability tier, honors one behavioral contract in this repo: lead with the outcome, prove completion with artifacts, decide depth-first rather than from a hunch, do not stop early, do the simplest thing that works well, and disclose every honest finding uncapped. For Claude Code, the full doctrine and its enforcement (an always-loaded rule, a launch-time system-prompt wrapper, an inert-by-default verification hook) live at .claude/standards/OPERATING-STANDARD.md; see docs/OPERATING-STANDARD.md. Tools without an equivalent mechanism should still hold every model to this same six-point contract, via whatever system-prompt or repo-instructions surface that tool exposes.
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.
- 8d ago First seen · 101 lines · 1,259 tokens per session scan A e310af265be6
claude-multi-agent-architecture AGENTS.md is an instructions file published in the GitHub repository mnzralee/claude-multi-agent-architecture (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,259 tokens to every session, about $0.0063 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 2026-08-31.
Other instructions, from other repositories
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).
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).
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.
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.