Agent skill

Task Runner

A skill your agent uses when you have a written implementation plan to execute in a separate session with review checkpoints

MITAuto-check passedAgent Workflows

Install Task Runner

skills CLI

$ npx skills add NoobyGains/godmode --skill task-runner -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install NoobyGains/godmode task-runner --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/NoobyGains/godmode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/task-runner .claude/skills/task-runner && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "task-runner" agent skill from https://github.com/NoobyGains/godmode/tree/master/skills/task-runner into .claude/skills/task-runner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-runner", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/NoobyGains/godmode/tree/master/skills/task-runner

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add NoobyGains/godmode --skill task-runner -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install NoobyGains/godmode task-runner --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/NoobyGains/godmode.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/task-runner .agents/skills/task-runner && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "task-runner" agent skill from https://github.com/NoobyGains/godmode/tree/master/skills/task-runner into .agents/skills/task-runner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-runner", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add NoobyGains/godmode --skill task-runner -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install NoobyGains/godmode task-runner --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/NoobyGains/godmode.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/task-runner .cursor/skills/task-runner && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "task-runner" agent skill from https://github.com/NoobyGains/godmode/tree/master/skills/task-runner into .cursor/skills/task-runner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-runner", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/NoobyGains/godmode.git --path skills/task-runner

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add NoobyGains/godmode --skill task-runner -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install NoobyGains/godmode task-runner --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/NoobyGains/godmode.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/task-runner .gemini/skills/task-runner && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "task-runner" agent skill from https://github.com/NoobyGains/godmode/tree/master/skills/task-runner into .gemini/skills/task-runner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-runner", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install NoobyGains/godmode task-runner

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add NoobyGains/godmode --skill task-runner -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/NoobyGains/godmode.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/task-runner .github/skills/task-runner && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "task-runner" agent skill from https://github.com/NoobyGains/godmode/tree/master/skills/task-runner into .github/skills/task-runner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-runner", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add NoobyGains/godmode --skill task-runner -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install NoobyGains/godmode task-runner --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/NoobyGains/godmode.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/task-runner .opencode/skills/task-runner && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "task-runner" agent skill from https://github.com/NoobyGains/godmode/tree/master/skills/task-runner into .opencode/skills/task-runner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-runner", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: task-runner
GitHub stars: 107
Token cost: ~2.2k tokens
SKILL.md length: 822 words
Files: 1
Skills in repo: 34
Repo updated: Mar 9, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

A skill your agent uses when you have a written implementation plan to execute in a separate session with review checkpoints

Works in 5 steps: Load and Scrutinize Plan → Execute Batch → Report → …
You have a written implementation plan to execute in a separate session with review checkpoints
SKILL.md covers Overview, The Prime Directive, When to Use and The Entry Protocol, plus 8 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Task Runner is an agent skill from NoobyGains/godmode. Use when you have a written implementation plan to execute in a separate session with review checkpoints

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Planning. The repository describes itself as: The AI development framework that thinks before it builds. 36 composable skills for Claude Code, Cursor, Codex, and OpenCode. The licence is MIT.

When your agent uses it

You have a written implementation plan to execute in a separate session with review checkpoints
Tasks that involve Planning

Example prompts

“/task-runner”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

Load and Scrutinize Plan
Execute Batch
Report
Continue
Finalize

What it can do on your machine

Read from SKILL.md and the folder at commit 441103a. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are dot).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Task Runner loads about 2.2k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 822 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~29
When it runs · the whole SKILL.md, loaded when a task matches: ~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from NoobyGains/godmode at commit 441103a, republished under its MIT licence (© NoobyGains). 822 words, ~2,161 tokens.

Download SKILL.mdSave it as .claude/skills/task-runner/SKILL.md (or your agent's skills folder).

name: task-runner
description: Use when you have a written implementation plan to execute in a separate session with review checkpoints

Task Runner

Overview

Load the plan, scrutinize it, execute tasks in batches, and pause for architect review between batches.

Core principle: Batch execution with checkpoints for architect oversight.

Announce at start: "I'm applying the task-runner skill to execute this implementation plan."

The Prime Directive

NO PLAN EXECUTION WITHOUT CRITICAL REVIEW OF EACH TASK FIRST

No exceptions. No workarounds. No shortcuts.

Plans contain errors, ambiguities, and outdated assumptions. Every task must be critically examined before execution begins. Blindly following a plan is not "efficiency" -- it is investing time in incorrect work.

When to Use

dot

digraph applicability {
    "Written plan exists?" [shape=diamond];
    "Tasks independent?" [shape=diamond];
    "Human reviews between batches?" [shape=diamond];
    "task-runner" [shape=box];
    "delegated-execution" [shape=box];
    "Manual execution" [shape=box];

    "Written plan exists?" -> "Tasks independent?" [label="yes"];
    "Written plan exists?" -> "Manual execution" [label="no - write plan first"];
    "Tasks independent?" -> "Human reviews between batches?" [label="yes"];
    "Tasks independent?" -> "Manual execution" [label="no - tightly coupled"];
    "Human reviews between batches?" -> "task-runner" [label="yes - architect reviews"];
    "Human reviews between batches?" -> "delegated-execution" [label="no - stay in session"];
}

Use task-runner when:

A written implementation plan exists (from task-planning or equivalent)
Tasks should execute in batches with human review between them
The architect wants to inspect progress and make corrections between batches
Working in a parallel session (separate from the planning session)

Use delegated-execution instead when:

Staying in the same session (no context switch)
Prefer automated two-stage review (spec + quality) over human review
Tasks are independent and can be dispatched to fresh subagents

Use manual execution when:

No written plan exists yet
Tasks are tightly coupled and need continuous human guidance
Exploratory work where a plan would be premature

The Entry Protocol

Before beginning plan execution, verify ALL of these:

Plan exists and is accessible - You have a path to a written plan file
Plan has been scrutinized - You have critically read every task and flagged concerns
Concerns are addressed - Questions and ambiguities have been raised and answered
Tests pass at baseline - Existing tests pass before any changes are made
Branch is clean - Working in a feature branch (not main/master), no uncommitted changes
Worktree is configured - Using git worktree for isolation (godmode:workspace-isolation)
Task checklist is populated - All tasks loaded into a tracking checklist

If any gate fails, STOP. Do not proceed until every gate passes.

Cognitive Traps

Rationalization	What Is Actually True
"The plan looks fine, skip review"	Plans contain errors. Review catches them before time is wasted on incorrect work.
"I'll review while executing"	Reviewing during execution means you are already committed. Review before starting.
"This task is self-explanatory"	Self-explanatory tasks conceal assumptions. Thirty seconds of review prevents thirty minutes of rework.
"Batching is slow, I'll do everything at once"	Batches exist for human review. Skipping review lets errors compound across all tasks.
"Tests are slow, skip verification this round"	Unverified batches hide failures. Debugging later costs more.
"The plan says X but Y seems better"	Raise it with your human partner. Silently deviating from the plan creates confusion.

The Process

Step 1: Load and Scrutinize Plan

Read the plan file
Review critically -- flag any questions or concerns about each task
If concerns: Raise with your human partner before starting
If no concerns: Build a task checklist and proceed

Step 2: Execute Batch

Default batch size: 3 tasks

For each task:

Mark as in_progress
Follow each step precisely (plan provides granular steps)
Run verifications as specified
Mark as completed

Show full SKILL.md (333 more words)Show less

Step 3: Report

When batch completes:

Show what was implemented
Show verification output
Say: "Ready for feedback."

Step 4: Continue

Based on feedback:

Apply changes if needed
Execute next batch
Repeat until all tasks are done

Step 5: Finalize

After all tasks are complete and verified:

Announce: "I'm applying the merge-protocol skill to finalize this work."
REQUIRED SUB-SKILL: Use godmode:merge-protocol
Follow that skill to verify tests, present options, execute choice

When to Stop and Ask

STOP executing immediately when:

You hit a blocker mid-batch (missing dependency, test failure, unclear instruction)
The plan has critical gaps that prevent starting
You do not understand an instruction
Verification fails repeatedly

Ask for clarification rather than guessing.

When to Revisit Earlier Steps

Return to Scrutiny (Step 1) when:

Partner updates the plan based on your feedback
The fundamental approach needs rethinking

Do not force through blockers -- stop and ask.

Guardrails

Never:

Execute a task you have not critically reviewed first
Skip verification steps to "save time"
Silently deviate from the plan without raising it with your human partner
Start implementation on main/master branch without explicit user consent

Always:

Review each task before marking it in_progress
Run verifications as specified in the plan after each task
Stop and ask when blocked (do not guess or improvise)
Report the completed batch and wait for feedback before continuing

Batch Execution Diagram

dot

digraph batch_flow {
    rankdir=TB;

    gate [label="Entry Protocol\n(all checks pass?)", shape=diamond];
    gate_fail [label="STOP\nResolve before proceeding", shape=box, style=filled, fillcolor="#ffcccc"];
    load [label="Load plan\nBuild task checklist", shape=box];
    review_task [label="Scrutinize next task", shape=box];
    concerns [label="Concerns?", shape=diamond];
    raise [label="Raise with\nhuman partner", shape=box, style=filled, fillcolor="#ffffcc"];
    execute [label="Mark in_progress\nExecute task steps\nRun verifications", shape=box];
    mark_done [label="Mark completed", shape=box];
    batch_done [label="Batch complete?\n(default: 3 tasks)", shape=diamond];
    report [label="Report results\nSay: Ready for feedback", shape=box, style=filled, fillcolor="#ccffcc"];
    feedback [label="Wait for\nhuman feedback", shape=box];
    apply [label="Apply adjustments\nif needed", shape=box];
    more [label="More tasks?", shape=diamond];
    finish [label="Invoke merge-protocol\nskill", shape=box, style=filled, fillcolor="#ccccff"];

    gate -> gate_fail [label="no"];
    gate -> load [label="yes"];
    load -> review_task;
    review_task -> concerns;
    concerns -> raise [label="yes"];
    raise -> review_task [label="resolved"];
    concerns -> execute [label="no"];
    execute -> mark_done;
    mark_done -> batch_done;
    batch_done -> review_task [label="no"];
    batch_done -> report [label="yes"];
    report -> feedback;
    feedback -> apply;
    apply -> more;
    more -> review_task [label="yes - next batch"];
    more -> finish [label="no - all done"];
}

Reminders

Scrutinize the plan critically before starting
Follow plan steps precisely
Do not skip verifications
Reference skills when the plan calls for them
Between batches: report and wait
Stop when blocked, do not guess
Never start implementation on main/master without explicit user consent

Connections

Required workflow skills:

godmode:workspace-isolation - REQUIRED: Set up isolated workspace before starting
godmode:task-planning - Creates the plan this skill executes
godmode:merge-protocol - Finalize development after all tasks

During execution, tasks may invoke:

godmode:test-first - When plan tasks involve writing new code
godmode:fault-diagnosis - When a task encounters unexpected failures
godmode:completion-gate - Verify each batch before reporting

Alternative workflow:

godmode:delegated-execution - Use for same-session execution with automated two-stage review instead of human-in-loop batches

Files

Just SKILL.md in skills/task-runner of NoobyGains/godmode.

Open the folder on GitHubat commit 441103a

Compare with similar skills

Task Runner next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Task Runner compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Task Runner this skillNoobyGains/godmode	107	—	~2.2k	Automated safety check: Pass	MIT	7 mo ago
Executing Plans Inlineobra/superpowers	296k	2 repos	~5.1k	Automated safety check: Pass	MIT	today
Interview Meaddyosmani/agent-skills	102k	6 repos	~3.8k	Automated safety check: Pass	MIT	4 days ago
OpenSpec Guided OnboardingFission-AI/OpenSpec	71k	1 repos	~4.5k	Automated safety check: Pass	MIT	yesterday
Writing Plansgeeksblabla/stateofdev.ma	163	56 repos	~661	Automated safety check: Pass	None	7 mo ago
Subagent Driven DevelopmentAsvarox/allkaraoke	261	37 repos	~1.2k	Automated safety check: Pass	None	today

Similar skills

Executing Plans Inline
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
296k GitHub starsUsed in 2 repos~5.1k tokens
Agent WorkflowsAuto-check passed
Interview Me
addyosmani/agent-skills
Asks one question at a time, each with a best guess attached, until the agent is about 95 percent sure what you really want, before any plan, spec or code.
102k GitHub starsUsed in 6 repos~3.8k tokens
Agent WorkflowsAuto-check passed
OpenSpec Guided Onboarding
Fission-AI/OpenSpec
Walks you through a complete OpenSpec workflow cycle with narration while doing real work in your codebase.
71k GitHub starsUsed in 1 repo~4.5k tokens
Agent WorkflowsAuto-check passed
Writing Plans
geeksblabla/stateofdev.ma
A skill your agent uses when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file…
163 GitHub starsUsed in 56 repos~661 tokens
Agent WorkflowsAuto-check passed
Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
261 GitHub starsUsed in 37 repos~1.2k tokens
Agent WorkflowsAuto-check passed
Planning With Files
jd-opensource/JoySafeter
Implements Manus-style file-based planning for complex tasks.
313 GitHub starsUsed in 18 repos~1.8k tokens
Agent WorkflowsAuto-check: notes

Questions about Task Runner

What does Task Runner do?

A skill your agent uses when you have a written implementation plan to execute in a separate session with review checkpoints. Task Runner is an agent skill from NoobyGains/godmode.

When should I use Task Runner?

Task Runner fits situations like: you have a written implementation plan to execute in a separate session with review checkpoints; tasks that involve Planning.

How do I install Task Runner in Claude Code?

Run `npx skills add NoobyGains/godmode --skill task-runner -a claude-code`. Or copy the skill folder (skills/task-runner in NoobyGains/godmode) into .claude/skills/task-runner in your project. Claude Code loads it when a task matches its description.

How do I install Task Runner in Codex?

Run `npx skills add NoobyGains/godmode --skill task-runner -a codex`. Or copy the skill folder (skills/task-runner in NoobyGains/godmode) into .agents/skills/task-runner in your project. Codex loads it when a task matches its description.

Can I use Task Runner in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NoobyGains/godmode --skill task-runner -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/task-runner, .gemini/skills/task-runner, .github/skills/task-runner and .opencode/skills/task-runner in your project.

What does Task Runner need to run?

SKILL.md names no scripts, command-line tools or credentials: Task Runner is instructions for the agent only.

Does Task Runner access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Task Runner safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Task Runner use?

Task Runner is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Task Runner use?

About 2.2k tokens (SKILL.md is roughly 8.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Task Runner?

Skills that share tags, products or a category with Task Runner: Executing Plans Inline (obra/superpowers, 296k stars), Interview Me (addyosmani/agent-skills, 102k stars), OpenSpec Guided Onboarding (Fission-AI/OpenSpec, 71k stars) and Writing Plans (geeksblabla/stateofdev.ma, 163 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Task Runner?

NoobyGains (a GitHub user) maintains it in NoobyGains/godmode, which has 107 GitHub stars. The repository holds 34 skills in this directory. The repository was last updated on March 9, 2026.

Source: NoobyGains/godmode on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Task Runner

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Task Runner

Overview

The Prime Directive

When to Use

The Entry Protocol

Cognitive Traps

The Process

Step 1: Load and Scrutinize Plan

Step 2: Execute Batch

Step 3: Report

Step 4: Continue

Step 5: Finalize

When to Stop and Ask

When to Revisit Earlier Steps

Guardrails

Batch Execution Diagram

Reminders

Connections

Files

Compare with similar skills

Similar skills

More from NoobyGains/godmode

Related

Questions about Task Runner