agentleFS
chacosoldierchacosoldier/compabob/.claude/skills/add-agent/SKILL.md

add-agent

Skill34 starsChanged 23 days agoMITView on GitHub

Scaffold a new specialized agent for this assistant. Use for "/add-agent", "create a new agent", or "I want an agent that does X".

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 2

    Distinctive

    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
  1. Distinctive:

    Create a new agent so the assistant grows with the user's work.

    line 8
  2. Very specific:

    Check for overlap: Read the existing agents in .claude/agents/.

    line 17
  3. Very specific:

    Register it: Add a one-line routing rule for the new agent to the Agent Architecture & Routing section of CONSTITUTION.md.

    line 19
  4. Distinctive:

    Keep the tool list minimal.

    line 25

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “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
SKILL.md

Add Agent

Create a new agent so the assistant grows with the user's work. This is the main way to customize the kit.

Steps

  1. Ask four things (one short round of questions, not an interrogation):
    • Name: kebab-case, e.g. recruiting or product-research.
    • Purpose and triggers: what it owns, and the phrases or domains that should route to it. This becomes the description, which is what actually drives routing.
    • Tools: the minimum it needs (4 to 6). Advice-only agents get read tools only: Read, Glob, Grep, WebFetch, WebSearch.
    • Model: inherit is the default (the agent follows the session's model); pin sonnet for a cheap, high-volume agent or opus for one that always needs hard reasoning.
  2. Check for overlap. Read the existing agents in .claude/agents/. If the new agent overlaps an existing one, say so and suggest either editing the existing agent or sharpening both descriptions so routing stays clean.
  3. Scaffold. Copy .claude/agents/_agent-template.md.template to .claude/agents/<name>.md and fill it in: frontmatter, Purpose, When to use / when not to, Output format, Safety.
  4. Register it. Add a one-line routing rule for the new agent to the Agent Architecture & Routing section of CONSTITUTION.md. (_orchestrator-reference.md describes coordination patterns; it is not a list of agents.)
  5. Test routing. Suggest two or three prompts that should land on the new agent, and one that should not (to confirm it does not over-trigger).

Principles

  • The description is the routing signal. Write it as "Use for X, Y, Z", and name what it is not for.
  • Keep the tool list minimal. An agent with every tool routes badly.
  • One agent, one job. If it needs a paragraph to describe, it is two agents.

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.