Borrowing it
Nothing to install: this file belongs to leonardsellem/codex-subagents-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.
curl -O https://raw.githubusercontent.com/leonardsellem/codex-subagents-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/leonardsellem/codex-subagents-mcpWrote 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/leonardsellem/codex-subagents-mcp/agents-md)<a href="https://agentmods.dev/instructions/leonardsellem/codex-subagents-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/leonardsellem/codex-subagents-mcp/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/leonardsellem/codex-subagents-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/leonardsellem/codex-subagents-mcp/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 | $0.00887 | $0.00887 |
| Opus 5.5 | $0.00355 | $0.00355 |
| Sonnet 5.5 | $0.00177 | $0.00177 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade B, and why
codex-subagents-mcp AGENTS.md scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Align metadata with Codex profiles you run under; enforce behavior in `~/.codex/config.toml`. How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents
Author custom sub‑agents without code changes by adding files to an agents registry directory. The MCP server loads definitions from agents/*.md and agents/*.json. Agent names map to file basenames (e.g., agents/perf.md registers agent perf). The server may include a few example built‑ins for demos, but prefer files on disk (or use an ad‑hoc inline agent when both persona and profile are provided).
- Point the server to your agents directory via
--agents-dirorCODEX_SUBAGENTS_DIR. It also auto-detects./agentsor./.codex-subagents/agentswhen not provided. - Keep personas task‑oriented and concise; avoid generic, unfocused instructions.
Markdown agent (frontmatter + persona)
Create agents/<name>.md:
---
profile: debugger
approval_policy: on-request # never | on-request | on-failure | untrusted
sandbox_mode: workspace-write # read-only | workspace-write | danger-full-access
---
You are a pragmatic performance analyst. Identify hotspots, propose minimal, measurable fixes, and outline validation steps with lightweight metrics.
Required: profile (loader defaults to default if omitted). Optional: approval_policy, sandbox_mode. The body is the persona text injected for the sub‑agent.
JSON agent
Create agents/<name>.json:
{
"profile": "debugger",
"persona": "You plan and validate safe DB migrations with rollbacks.",
"approval_policy": "on-request",
"sandbox_mode": "workspace-write"
}
Required: profile, persona. Optional: approval_policy, sandbox_mode.
Tips
- Validate registry:
tools.call name=validate_agents(optionally pass{ "dir": "/abs/path" }). - List available agents:
tools.call name=list_agents. - Align metadata with Codex profiles you run under; enforce behavior in
~/.codex/config.toml. - Keep personas short, specific, and action‑biased; prefer concrete checklists over philosophy.
- See also:
docs/OPERATIONS.md.
Usage Hint
When a task matches a sub‑agent specialty, call the MCP tool:
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 · 77 lines · 887 tokens per session scan B a2d41709d145
codex-subagents-mcp AGENTS.md is an instructions file published in the GitHub repository leonardsellem/codex-subagents-mcp (161 stars, last pushed 10mo ago), licensed MIT. It adds 887 tokens to every session, about $0.0035 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
codex-subagents-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| codex-subagents-mcp AGENTS.mdleonardsellem/codex-subagents-mcp | Instructions file | 161 | 10mo ago | MIT | B | 887 | Codex, OpenCode |
| 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 |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |