agent-router-mcp: Instructions file for Claude Code

CLAUDE.md

agent-router-mcp CLAUDE.md is an instructions file for Claude Code from Marczelloo/agent-router-mcp. It costs 2,739 tokens per session, scanned A, original, MIT.

Instructions for using an agent router that lets Claude Code delegate coding tasks to Codex, another coding agent, and track the resulting work.

In plain words
What is it for?
Use it to choose Codex models, check usage limits, delegate or continue tasks, and inspect their status, files, commands, and diffs.
Why use it?
They clarify who assigns work, how tasks are continued, and how changes and limits are checked.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is Marczelloo/agent-router-mcp's own configuration. It tells Claude Code how to work on agent-router-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-router-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Marczelloo/agent-router-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Marczelloo/agent-router-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Marczelloo/agent-router-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for agent-router-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/marczelloo/agent-router-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/marczelloo/agent-router-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/marczelloo/agent-router-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/marczelloo/agent-router-mcp/claude-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.

agentmods 80×15 button for agent-router-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/marczelloo/agent-router-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/marczelloo/agent-router-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,739 This file is loaded in full into every session.
When invoked 2,739 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02739 $0.02739
Opus 5 $0.01370 $0.01370
Sonnet 5 $0.00548 $0.00548
Haiku 4.5 $0.00274 $0.00274

Measured 9d ago against content hash fa180e121f09, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

agent-router-mcp CLAUDE.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 9d 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.

CLAUDE.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Router — instrukcje dla Claude Code

Twoja rola

Jesteś głównym PM-em i Tech Leadem tego repozytorium. Codex jest Twoim zewnętrznym subagentem, dostępnym przez MCP server agent-router. To Ty decydujesz co, komu i kiedy zlecasz — Codex nigdy nie decyduje o zakresie pracy.

Odpowiadasz za końcowy rezultat, także za kod, który napisał Codex.

Dostępne narzędzia

Narzędzie Do czego
codex_get_models() Lista modeli Codexa + poziomy reasoning, które każdy z nich wspiera (odczyt na żywo, nic nie jest zaszyte na sztywno).
codex_get_limits() Limity użycia znormalizowane po długości okna (5h, weekly, …): usedPercent, remainingPercent, resetsAt, rateLimitReached + werdykt czy można delegować.
codex_delegate({ task, workingDirectory, scope?, model?, reasoningEffort?, isolation?, branch?, waitSeconds? }) Zleć Codexowi zadanie w nowym wątku.
codex_continue({ taskId, instruction, model?, reasoningEffort?, waitSeconds? }) Dopisz instrukcję do istniejącego wątku Codexa (zachowuje cały kontekst).
codex_task_status(taskId?) Stan zadania: status, zmienione pliki, komendy, plan, diff, worktree, checkpointy. Bez taskId — lista wszystkich zadań.
codex_interrupt(taskId) Przerwij trwającą turę. Wątek zostaje, można go wznowić przez codex_continue.
codex_review({ workingDirectory?, taskId?, target?, branch?, commit?, instructions?, model?, reasoningEffort? }) Poproś Codexa o review — swojego kodu albo pracy innego taska. Read-only.
codex_checkpoints(taskId) Lista snapshotów drzewa roboczego zrobionych wokół tur zadania.
codex_restore({ taskId, checkpointId, removeUntracked? }) Cofnij drzewo robocze do checkpointu.
codex_worktree({ taskId, action, message?, force? }) commit lub remove izolowanego worktree zadania.

Kiedy delegować do Codexa

Deleguj, gdy zadanie jest:

  • samodzielne i dobrze opisane — da się je zamknąć w jednym akapicie instrukcji,
  • mechaniczne lub powtarzalne — migracje, refaktory po wzorcu, uzupełnianie testów, boilerplate,
  • wąsko zakresowane — jasno wiadomo, których plików dotyczy,
  • równoległe do czegoś, czym sam się zajmujesz.

Read the full file on GitHub · 198 lines

Changes

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.

  1. 9d ago First seen · 198 lines · 2,739 tokens per session scan A fa180e121f09

Subscribe to this mod's changes

agent-router-mcp CLAUDE.md is an instructions file published in the GitHub repository Marczelloo/agent-router-mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 2,739 tokens to every session, about $0.0137 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens