unlimited-mcp: Instructions file for Codex

AGENTS.md

unlimited-mcp AGENTS.md is an instructions file for Codex, OpenCode from triumsebas/unlimited-mcp. It costs 5,459 tokens per session, scanned A, original, Apache-2.0.

A set of instructions for unlimited-mcp, a local service that sends coding work to other tools or specialized workers. It explains how to inspect available workers and choose between local and TypeScript-based execution.

In plain words
What is it for?
Use it when coordinating work through unlimited-mcp, checking its configured capabilities and allowed folders, or deciding whether a task should be delegated or handled directly.
Why use it?
Delegating work without first checking available workers or safety limits can send a task to the wrong place. These instructions define the required first check and the decisions for handling each job.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: runs codex exec, but also the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is triumsebas/unlimited-mcp's own configuration. It tells Codex and OpenCode how to work on unlimited-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 unlimited-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to triumsebas/unlimited-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/triumsebas/unlimited-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/triumsebas/unlimited-mcp

Made for: Codex, OpenCode.

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 unlimited-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/triumsebas/unlimited-mcp/agents-md.svg)](https://agentmods.dev/instructions/triumsebas/unlimited-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/triumsebas/unlimited-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/triumsebas/unlimited-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,459 This file is loaded in full into every session.
When invoked 5,459 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 $0.05459 $0.05459
Opus 5 $0.02729 $0.02729
Sonnet 5 $0.01092 $0.01092
Haiku 4.5 $0.00546 $0.00546

Measured 6d ago against content hash 0d9d5a0d657d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

unlimited-mcp 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 6d 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.

AGENTS.md · 527 lines

How it starts

The opening of the file, as written. The whole thing — 527 lines — stays where its author put it; the contents beside it link to each section on GitHub.

unlimited-mcp — orchestrator companion (Codex / generic)

This file is for Codex CLI and generic MCP orchestrators. Codex reads AGENTS.md natively, so it is kept self-contained.

This is the single source of truth for orchestration guidance. CLAUDE.md imports this file and the /delegate skill references it — when the tool surface or workflow changes, edit here, not in those. Claude Code users: see CLAUDE.md for the Claude-specific deltas.

Repository language — English only. All files committed to this repository — code, comments, identifiers, commit messages, and Markdown/docs — must be written in English, so the project stays readable for international developers.


What this MCP does

unlimited-mcp lets you delegate work to cheaper or specialised workers (aider, opencode, smolagents, raw commands) without blocking your context window. Every tool returns a JobResult — a structured object you can parse for status, summary, diff_ref, and raw_output_ref.


First call: list_capabilities()

Always call this first after connecting. It returns what agents, providers, and tools are configured, plus the current allowed_roots and safety policy.


Queue selection: local · ts · ts_serial

Scenario queue= Why
Quick command, analysis, < 30s "local" (default) In-process thread, no ts dependency
Independent tasks, run in parallel "ts" Up to 4 simultaneous jobs; durable across restarts
Ordered pipeline (step 2 needs step 1 done) "ts_serial" Strictly 1 job at a time; enqueue all upfront
Any task expected to take > 1 min "ts" or "ts_serial" Don't block context; recoverable from inbox

Default rule: if the task is expected to take more than 2 minutes, use "ts" or "ts_serial". No exceptions.

  • Multiple independent tasks, or single long task → "ts".
  • Ordered pipeline where steps don't depend on each other's output → "ts_serial".
  • Steps where you must read the result before deciding the next step → poll with "local".
  • Quick commands (< 2 min) you'll poll in the same turn → "local".

Read the full file on GitHub · 527 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. 6d ago First seen · 527 lines · 5,459 tokens per session scan A 0d9d5a0d657d

Subscribe to this mod's changes

unlimited-mcp AGENTS.md is an instructions file published in the GitHub repository triumsebas/unlimited-mcp (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 5,459 tokens to every session, about $0.0273 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 · 5,182 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

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

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