agentleFS
Sign inStart free
ANAMIZEDANAMIZED/SuperAgenticMCP/AGENTS.md

SuperAgenticMCP

AGENTS.md1 starsChanged 3 months agoApache-2.0View on GitHub

This file is the contract for any AI coding agent working on this repository. Layout standard: Server OS See docs/LAYOUT.md. SuperAgenticMCP is the switchboard for agent swarms: an MCP-native router and multi-agent control plane that racks MCP servers, plans tasks (planner → workers → critic), routes by capability then latency, streams steps to a live board + JSONL log, and files runs into a memory-scope constellation. A senior engineer with only the source code and README.md must be able to…

  • Installs packages
  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository4 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

4 rules. About 1 is common, 2 are distinctive, and 1 is very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Never break the verify contract (scripts/verify.sh).

    line 33
  2. Common:

    Keep secrets out of source and the hero HTML.

    line 36
  3. Distinctive:

    Prefer small, focused changes.

    line 38
  4. Distinctive:

    Do not invent a parallel layout — Server OS is the permanent standard.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AGENTS.md — SuperAgenticMCP

This file is the contract for any AI coding agent working on this repository.

Layout standard: Server OS
See docs/LAYOUT.md.

What this project is

SuperAgenticMCP is the switchboard for agent swarms: an MCP-native router and multi-agent control plane that racks MCP servers, plans tasks (planner → workers → critic), routes by capability then latency, streams steps to a live board + JSONL log, and files runs into a memory-scope constellation.

A senior engineer with only the source code and README.md must be able to install, exercise public surfaces, and verify via scripts/verify.sh.

How to run & verify

pip install -e ".[dev]"
make test
bash scripts/verify.sh

MCP: superagenticmcp
CLI: superagenticmcp-cli status
Hero: superagenticmcp.html
WebMCP board: web/board.html

Hard rules for agents

  1. Never break the verify contract (scripts/verify.sh).
  2. Fail closed — no silent drops of tool calls or servers.
  3. Capabilities and allow-lists only — no ambient authority.
  4. Keep secrets out of source and the hero HTML.
  5. Simulation belongs only in the browser demo; the real server path must not invent tool results.
  6. Prefer small, focused changes. Update README.md and AGENTS.md when public surfaces change.
  7. Do not invent a parallel layout — Server OS is the permanent standard.
  8. WebMCP is a page front door. Do not replace stdio MCP with it.

Surfaces that must stay working

MCP Server, CLI, SDK import, skills frontmatter, AGENTS.md, scripts/verify.sh, CI, web/board.html.

See docs/WEBMCP.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free