Agent Plugins Marketplace
All plugins

idle-skills

v0.9.0

Multi-agent development on a shared record of work. An interview turns a dropped task into a goal and a plan you own; a planner breaks it into goals, builders and reviewers work them, and you contradict what is not done.

CodexClaude Code15 Skills

By AmbroviaLicense: Apache-2.00 GitHub starsUpdated 2 days ago

Directory evidence

Runtimes
Codex and Claude Code
Parsed components
15 skill or MCP entries
Source updated
Sep 21, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology

Install idle-skills for Codex and Claude Code

Installs for the current user
codex plugin marketplace add ambrovia/idle-agent-tools
codex plugin marketplace upgrade idle-agent-tools
codex plugin add idle-skills@idle-agent-tools

Paste and run these commands in a terminal with Codex. They add and refresh the idle-agent-tools catalog, then install this plugin.

Compatibility: the page URL and API slug “idle-skills” remain stable.

  • Codex: idle-skills@agent-plugin-marketplaceidle-skills@idle-agent-tools

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/ambrovia/idle-agent-tools

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

idle-skills/
├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
├── skills/architecture/SKILL.md
├── skills/architecture-critique/SKILL.md
├── skills/compound/SKILL.md
├── skills/design/SKILL.md
├── skills/lore/SKILL.md
├── skills/pipeline/SKILL.md
├── skills/program-design/SKILL.md
├── skills/refine/SKILL.md
├── skills/retro/SKILL.md
├── skills/review/SKILL.md
├── skills/setup/SKILL.md
├── skills/ship/SKILL.md
├── skills/write-code/SKILL.md
├── skills/write-docs/SKILL.md
└── skills/write-tests/SKILL.md

Included Skills15

architectureskills/architecture/SKILL.md

Work out the technical shape of an agreed plan — contracts, types, schemas, dependency order — and propose it as tasks and decisions. Use only where scope and complexity make those definitions necessary. Never decides how the program works; that is the plan's job.

architecture-critiqueskills/architecture-critique/SKILL.md

Read-only critique of a proposed technical breakdown against the plan, before it is accepted. Checks alignment, necessary contracts, feasibility, simplicity and readability. Requested when worth challenging, never scheduled; reports blockers without scoring or rewriting.

compoundskills/compound/SKILL.md

Review accumulated retros, identify recurring evidence-backed process patterns, and propose surgical skill or workflow changes for human approval. Never applies changes automatically.

designskills/design/SKILL.md

Decide consequential UX/UI behavior for an agreed task. Use when a changed user-facing surface is not already determined by an existing approved pattern and a design system is configured. Skip backend/infra and trivial pattern-following changes.

loreskills/lore/SKILL.md

Capture, scan, or index terse, currently actionable tribal knowledge about non-obvious cross-cutting constraints, workarounds, and gotchas. Use when missing context would cause a future mistake; never use lore as history, a changelog, or a second requirements system.

pipelineskills/pipeline/SKILL.md

Drive one or more tasks to a CI-green PR, through whatever shape each one actually needs. Runs the interviews itself, breaks the work into goals with the maintainer, and dispatches the rest. Never creates scope.

program-designskills/program-design/SKILL.md

Interview the maintainer about how the program should work, and write it into the plan in plain words. Use when the approach is not obvious. Produces the how-it-works half of the plan — no contracts, types, or schemas.

refineskills/refine/SKILL.md

Interview the maintainer about what they need from a task, and write it into the task in their words. Use when a dropped task's value, boundary, or a load-bearing noun is not already settled. Skip when it is already clear enough to build from.

retroskills/retro/SKILL.md

Record concrete successes and friction after a task, session, or pipeline run. Observe from artifacts and trajectories without fixing, assigning work, or changing process.

reviewskills/review/SKILL.md

Read-only review of implemented work against its task's goal or an explicit changed-file scope. Judges whether the goal is reached, applicable constraints/rules, regressions, and plausible changed risks. Produces operational findings and a verdict; never edits code.

setupskills/setup/SKILL.md

Configure evidence-backed, maintainer-approved pipeline rule slots and design-system paths for this repository. Use during installation or when repository conventions change; do not promote generic best practices into binding policy automatically.

shipskills/ship/SKILL.md

Turn completed work into a clean CI-green merge-ready PR. Verifies, commits, updates the PR, and waits for CI; does not merge. Review belongs to the pipeline skill.

write-codeskills/write-code/SKILL.md

Implement a claimed task with the smallest clear solution that reaches its goal. Use after the plan is agreed and the task is yours.

write-docsskills/write-docs/SKILL.md

Write or review user-facing documentation when it is an explicit deliverable or when an implementation makes authoritative documentation false. Preserve project voice and factual accuracy; use reading-funnel craft proportionately to page type.

write-testsskills/write-tests/SKILL.md

Create proportionate failing evidence for a task's goal before implementation when behavior is regressible and an automated test is appropriate. Use in the build phase; do not let tests create requirements.

Plugin manifests2

.codex-plugin/plugin.json
{
  "name": "idle-skills",
  "description": "Multi-agent development on a shared record of work. An interview turns a dropped task into a goal and a plan you own; a planner breaks it into goals, builders and reviewers work them, and you contradict what is not done.",
  "version": "0.9.0",
  "author": {
    "name": "Ambrovia"
  },
  "homepage": "https://github.com/ambrovia/idle-agent-tools",
  "repository": "https://github.com/ambrovia/idle-agent-tools",
  "license": "Apache-2.0",
  "keywords": [
    "skills",
    "pipeline",
    "multi-agent",
    "tdd",
    "review"
  ],
  "skills": "./skills",
  "interface": {
    "displayName": "Idle Skills",
    "shortDescription": "Interview, plan, build, review and ship on a shared record of work.",
    "longDescription": "Multi-agent development on a shared record of work. An interview turns a dropped task into a goal and a plan you own; a planner breaks it into goals, builders and reviewers work them, and you contradict what is not done. Skills cover refinement, program design, design, architecture, implementation, review, documentation, retro and shipping. Works on the idle-tasks record of work.",
    "developerName": "Ambrovia",
    "category": "Productivity",
    "capabilities": [
      "Interactive",
      "Write",
      "Review"
    ],
    "websiteURL": "https://github.com/ambrovia/idle-agent-tools",
    "defaultPrompt": [
      "Run /pipeline for this item.",
      "Register a new work item.",
      "Review this change with the pipeline."
    ],
    "brandColor": "#2563EB"
  }
}
.claude-plugin/plugin.json
{
  "name": "idle-skills",
  "description": "Multi-agent development on a shared record of work. An interview turns a dropped task into a goal and a plan you own; a planner breaks it into goals, builders and reviewers work them, and you contradict what is not done.",
  "version": "0.9.0",
  "author": {
    "name": "Ambrovia"
  },
  "homepage": "https://github.com/ambrovia/idle-agent-tools",
  "repository": "https://github.com/ambrovia/idle-agent-tools",
  "license": "Apache-2.0",
  "skills": "./skills",
  "agents": [
    "./agents/pipeline-planner.md",
    "./agents/pipeline-reviewer.md",
    "./agents/pipeline-builder.md"
  ],
  "dependencies": [
    "idle-tasks"
  ]
}

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[idle-skills on Agent Plugins Marketplace](https://pluginsmp.com/plugins/idle-skills)