Agent Plugins Marketplace
← All plugins

task-runner

v0.35.0

Disciplined task execution: one task at a time, scope locked to the task, bounded verify-fix inner loop per task, no drift, no unbounded outer loop. Completion means every check passed with evidence — held at Stop by candor's gate (clause 4) when candor is installed; without it a run can end by narration. Ships the shared task-executor agent — the delegatable 'apply the fixes' sink every review routes to — a PostToolUse scope-lock tripwire, parallel-planning (/task-runner:plan), and the subagent discipline (the orchestration plugin was merged in on 2026-09-14): delegation contracts, verification panels, scripts/dispatch-lint.sh, and the ultra-assess boost hook.

Claude Code5 Skills

By Ivan-WG1 GitHub starsUpdated last week

Directory evidence

Runtimes
Claude Code
Parsed components
5 skill or MCP entries
Source updated
Sep 15, 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 task-runner for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install task-runner@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

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/galaykos/cc-marketplace

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

Plugin files

plugins/task-runner/
├── .claude-plugin/plugin.json
├── skills/code-redteam/SKILL.md
├── skills/delegation-contracts/SKILL.md
├── skills/task-execution/SKILL.md
├── skills/track-orchestration/SKILL.md
└── skills/verification-panels/SKILL.md

Included Skills5

code-redteamskills/code-redteam/SKILL.md

Use when a boosted (ultra/goal) run produced code and the diff must be red-teamed before trust — N=3 blind refuter panel plus completeness-critic over the SHIPPED code, not just spec/cards.

delegation-contractsskills/delegation-contracts/SKILL.md

Use when spawning subagents, delegating via Task/Agent, writing an agent prompt, planning a fan-out, or reading a subagent report — prompt contracts, evidence-backed compressed returns, model/effort tiering. Owns HOW to phrase and verify the dispatch; WHAT to split is code-architecture:plan-before-code, and pricing parallel execution is task-runner:parallel-planning.

task-executionskills/task-execution/SKILL.md

Use when executing a list of defined tasks (taskmaster cards, a plan's sequence, a todo list) — one task at a time, scope locked, bounded implement-verify-fix loop per task, status tracking, halt-with-evidence instead of drifting.

track-orchestrationskills/track-orchestration/SKILL.md

Use when /task-runner:run is invoked with --tracks[=N] — independent milestones as concurrent worktree-per-milestone tracks in dependency waves, merged by a sole-writer orchestrator. Not for serial runs (task-execution).

verification-panelsskills/verification-panels/SKILL.md

Use when deciding whether agent findings can be trusted, verifying subagent output, planning a review fan-out, judging competing solutions, or when discovery may stop too early — refuter voting, judge panels, loop-until-dry, completeness-critic.

Plugin manifests1

plugins/task-runner/.claude-plugin/plugin.json
{
  "name": "task-runner",
  "version": "0.35.0",
  "description": "Disciplined task execution: one task at a time, scope locked to the task, bounded verify-fix inner loop per task, no drift, no unbounded outer loop. Completion means every check passed with evidence — held at Stop by candor's gate (clause 4) when candor is installed; without it a run can end by narration. Ships the shared task-executor agent — the delegatable 'apply the fixes' sink every review routes to — a PostToolUse scope-lock tripwire, parallel-planning (/task-runner:plan), and the subagent discipline (the orchestration plugin was merged in on 2026-09-14): delegation contracts, verification panels, scripts/dispatch-lint.sh, and the ultra-assess boost hook.",
  "author": {
    "name": "Ivan-WG",
    "email": "[email protected]"
  },
  "keywords": [
    "worker",
    "process",
    "generic"
  ]
}

For maintainers

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

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