claude

agents

Recruit and onboard an agent like a new colleague: brief, role, routines, a TLC-checked wake chart and a trial of every safeguard, routed by recruit.

0 on GitHubby Russell Heillingv0.2.1MITupdated 5 days ago
/

Plugin agents from marketplace minime in chewcorp/minime. Commands read from the repo's manifest — 5 days ago.

What it installs

Skills (7)

  • brief

    Use when an agent to be built or rebuilt has no accepted brief, or the recruit script prints brief. Interviews the human and writes brief.md (problem, outcomes with numeric fits, non-goals, authority limits, attention budget, open decisions), then goldfish-reviews it for comprehension. Writes no cha

  • chart-duties

    Use when the recruit script prints chart-duties with routine IDs. Instantiates the standard wake statechart for each routine, adds the agent's own rules as invariants, checks it with TLC, and records which guards the host does not provide. Does not write the charter.

  • goldfish-review

    Use when a recruit artifact (brief, role or routines) needs review before the next stage. Parallel goldfish reviewers read only the artifact and its sources, never the conversation; you merge and verify their findings. Called by brief, role and routines.

  • recruit

    Use when the user asks to build, rebuild or govern an agent (a bot, seat or scheduled routine) with the minime agents loop, or names one of its stages (brief, role, routines, chart-duties, trial). Sets up the work folder, then loads the stage the routing script names. For a one-line prompt edit the

  • role

    Use when an agent has an accepted brief but no role, or the recruit script prints role. Writes role.md - what the agent owns, reads and must never do, its identity, and its split with any actor already in the same role - then goldfish-reviews it.

  • routines

    Use when an agent has an accepted role but its wakes are not written down, or the recruit script prints routines. Writes routines.md - one section per trigger with input as a delta, done-when, budgets, silence rule and approval gate - then goldfish-reviews it.

  • trial

    Use when every routine has a checked chart and the recruit script prints trial. Proves each control fires on a known input and stays quiet on a clean one, runs behavioural cases inside a real model in a throwaway HOME, and writes proof.json keyed to the tree hash.

Subagents (1)

  • agent-review

    Fresh-context (goldfish) review of a recruit artifact (brief, role, routines) against its intent and repo conventions. Runs checks, never edits; reports findings.

View source on GitHub

More from chewcorp/minime

All 2 plugins →

coder

claude

Staged delivery loop with planner, researcher, implementor, reviewer, approver and advisor subagents.

6 skills · 6 agents

0

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Maintain agents?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins2 plugins