mx-workflow / commands
AGENTS.md1 starsChanged 3 months agoMITView on GitHub
List available agents and their purposes
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 32,671 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 repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- comment-analyzerSkill
- hallucination-checkSkill
- silent-failure-hunterSkill
- type-design-analyzerSkill
The file
We split this agents.md into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Use Glob to find all .md files in the agents/ directory.
- Very specific: line 24
Use Grep to search all files in the commands/ directory for references to each agent name.
- Distinctive: line 46
Keep the purpose column concise — one short sentence, no more than 60 characters.
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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.
Files
List Available Agents
Scan the agents/ directory and display a formatted table of all available agents, their purposes, and which commands reference them.
Instructions
Step 1: Discover Agents
Use Glob to find all .md files in the agents/ directory.
Step 2: Read Agent Details
For each agent file found, read the file and extract:
- Name: from the
namefield in YAML frontmatter (or derive from filename by removing.md) - Description/Purpose: from the
descriptionfield in YAML frontmatter. Summarize to one short sentence if the description is long.
Step 3: Find Command References
Use Grep to search all files in the commands/ directory for references to each agent name. Record which commands mention each agent.
Step 4: Display Results
Output a formatted table like this:
AVAILABLE AGENTS
================
| Agent | Purpose | Used By |
|--------------------------|------------------------------------------------------|--------------------------------|
| mx-code-reviewer | Review code against guidelines and detect bugs | /implement, /pr |
| mx-code-simplifier | Simplify code for clarity while preserving function | /implement |
| ... | ... | ... |
Total: <N> agents
TIP: Agents run automatically via commands like /mx:implement and /mx:pr.
They can also be invoked directly via the Task tool for standalone analysis.Keep the purpose column concise — one short sentence, no more than 60 characters. If no commands reference an agent, show "standalone" in the Used By column.
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
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.

