agentsclimarketplace

Mission control agents md

Skill MN755/Codex-Mission_Control/apps/mcp-server/src/mission_control_mcp_server/_bundled/skills/mission-control-agents-md

An Open Source Platform For Building Projects With OpenAI's Codex, Claude CLI, And Other Coding LLMs Using Multi-Agent Swarms And Customizable Workflows. Runs On Windows, MacOS, And Linux.

Install
npx -y skills add MN755/Codex-Mission_Control --skill mission-control-agents-md

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Generate or review AGENTS.md from Mission Control understanding. Use when the user wants AGENTS.md proposed from the codebase map, existing instructions reviewed, or a safe draft prepared before writing.

SKILL.md

2.0 KB, 365 tokens by cl100k_base, as published. Nobody here has run it

Mission Control Agents Md

Purpose

Use Mission Control understanding to propose or review AGENTS.md safely.

The Codex chat agent is not the Mission Control Manager. It is the bridge between the user and the Mission Control Manager.

Use when

  • The user asks for AGENTS.md generation or review.
  • A repo needs agent instructions grounded in actual codebase structure.
  • You need to compare existing AGENTS.md guidance against Mission Control understanding.

Workflow

  1. Read the codebase map resource.
  2. Check AGENTS.md status or proposal tooling.
  3. Call mission_control_generate_agents_md or the proposal path when available.
  4. Summarize proposed sections and ask before writing any file changes.

Mission Control calls

Tools:

  • mission_control_generate_agents_md

Resources:

  • mission-control://projects/{project_id}/codebase-map
  • mission-control://projects/{project_id}/status

User-facing output

  • Include project overview, setup commands, run commands, test commands, build commands, architecture notes, coding rules, do-not-touch areas, safety rules, and completion report format.
  • Tell the user whether the result is a proposal or a written file.

Approval behavior

Always ask before writing or replacing AGENTS.md, even if the proposal looks good.

Never do

  • Do not invent setup commands that are not backed by the repo or Mission Control understanding.
  • Do not overwrite existing AGENTS.md silently.
  • Do not expose secret paths or tokens.

Failure and fallback

If AGENTS.md tooling is not available, use the codebase map to produce a bridge-safe draft summary and clearly mark file generation as expected or future.

Example invocation

Use Mission Control to propose an AGENTS.md for this repo.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.