What is codex-specialized-subagents AGENTS.md?

Repository-specific instructions for codex-specialized-subagents, an MCP server that lets Codex delegate work to separate coding-agent processes. MCP is a standard way for tools and models to communicate.

Use them when developing, testing, building, or reviewing this Node.js and TypeScript MCP server.

They provide the project context, real commands, and security rules needed to make safe, verifiable changes.

How leonardsellem/codex-specialized-subagents configures Codex and Ope

Reuse

Borrowing it

Nothing to install: this file belongs to leonardsellem/codex-specialized-subagents. 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/leonardsellem/codex-specialized-subagents/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/leonardsellem/codex-specialized-subagents

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/leonardsellem/codex-specialized-subagents/agents-md/github.svg)](https://agentmods.dev/instructions/leonardsellem/codex-specialized-subagents/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/leonardsellem/codex-specialized-subagents/agents-md"><img src="https://agentmods.dev/badge/instructions/leonardsellem/codex-specialized-subagents/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/leonardsellem/codex-specialized-subagents/agents-md"><img src="https://agentmods.dev/badge/instructions/leonardsellem/codex-specialized-subagents/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 916 This file is loaded in full into every session.

When invoked 916 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.

Model	Per session	Once invoked
Fable 5.1	$0.00916	$0.00916
Opus 5.5	$0.00366	$0.00366
Sonnet 5.5	$0.00183	$0.00183
Haiku 4.5	$0.00092	$0.00092

Measured 2mo ago against content hash 136ad287a894, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codex-specialized-subagents 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 2mo 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 · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file is for AI coding agents.

Keep it short. Use hierarchical, nearest-wins AGENTS.md files:

Root = global defaults + JIT map
Subfolders = concrete commands + patterns for that scope

Project snapshot

Name: codex-specialized-subagents
What is this? MCP server that lets Codex delegate to isolated codex exec sub-agents, selecting repo+global skills automatically.
Repo type: single project
Primary stack: Node.js + TypeScript + @modelcontextprotocol/sdk + zod

Root commands (verify these are real)

Install: npm install
Dev: npm run dev
Build: npm run build
Test: npm test
Integration test (requires codex CLI + auth): RUN_CODEX_INTEGRATION_TESTS=1 npm test
Lint/typecheck: npm run lint

Universal conventions

Default to small, finishable steps.
State assumptions + open questions explicitly.
Prefer pointers (paths + search commands) over long prose in AGENTS.
Verify before claiming “done”.

Security & secrets

Never commit secrets/tokens/keys.
Put secrets in .env/secret manager; .env is gitignored.
Avoid pasting secrets from ${CODEX_HOME:-~/.codex} (it may contain auth/config).

JIT directory map (nearest-wins)

.agent/ → .agent/AGENTS.md (ExecPlans + artifacts workflow)
.codex/skills/ → .codex/skills/AGENTS.md (repo-local skill authoring)
docs/ → (human-facing docs; user + contributor guides)
src/ → src/AGENTS.md (MCP server + tool implementations)
scripts/ → scripts/AGENTS.md (helper scripts)
.githooks/ → .githooks/AGENTS.md (optional git hooks)

As the repo grows:

apps/<name>/ → apps/<name>/AGENTS.md
packages/<name>/ → packages/<name>/AGENTS.md
services/<name>/ → services/<name>/AGENTS.md
Add docs/AGENTS.md only if docs need scope-specific agent rules.

Planning (ExecPlans)

Rules live in: .agent/PLANS.md
Create plans in: .agent/execplans/
Archive completed plans in: .agent/execplans/archive/
Debug journal: .agent/DEBUG.md (local-only by default)

Read the full file on GitHub · 81 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.

2mo ago First seen · 81 lines · 916 tokens per session scan A 136ad287a894

Subscribe to this mod's changes

codex-specialized-subagents AGENTS.md is an instructions file published in the GitHub repository leonardsellem/codex-specialized-subagents (69 stars, last pushed 10mo ago), licensed MIT. It adds 916 tokens to every session, about $0.0037 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.

Building agents codex-cli mcp mcp-server skills

codex-specialized-subagents AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
codex-specialized-subagents AGENTS.mdleonardsellem/codex-specialized-subagents	Instructions file	69	10mo ago	MIT	A	916	Codex, OpenCode
repobrain copilot-instructions.mdstudy8677/repobrain	Instructions file	1.4k	14d ago	MIT	A	229	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot

codex-specialized-subagents: Instructions file for Codex