New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Plan Management

by ntorga in ntorga/agent-starter-kit

Plan lifecycle — grill entry point, grounding, artifact review, per-epic execution, revision.

MITAuto-check passedAI & LLM Engineering

Install Plan Management

skills CLI
$ npx skills add ntorga/agent-starter-kit --skill plan-management -a claude-code

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

GitHub CLI
$ gh skill install ntorga/agent-starter-kit plan-management --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/ntorga/agent-starter-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/plan-management .claude/skills/plan-management && 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/

Facts

Skill name
plan-management
GitHub stars
146
Token cost
~1.8k tokens
SKILL.md length
848 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

Plan lifecycle — grill entry point, grounding, artifact review, per-epic execution, revision.

  • Works in 2 steps: Run the grill. Read and follow… → Confirm. Present the artifacts to the…
  • AI & LLM Engineering work in your project
  • SKILL.md covers Purpose, Procedure and Guardrails
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Plan Management is an agent skill from ntorga/agent-starter-kit. Plan lifecycle — grill entry point, grounding, artifact review, per-epic execution, revision.

Its SKILL.md is about 1.8k 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 AI & LLM Engineering. The repository describes itself as: The scaffold for your multi-model, personalized Natural Language AI Harness (NLAH) . The licence is MIT.

When your agent uses it

  • AI & LLM Engineering work in your project

Example prompts

  • “/plan-management”

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. Run the grill. Read and follow skills/grill/SKILL.md.
  2. Confirm. Present the artifacts to the user. Do not act until the user confirms shared understanding.

What it can do on your machine

Read from SKILL.md and the folder at commit 851e942. 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 bash).

    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

Plan Management loads about 1.8k tokens when it runs. Until then it costs about 27 tokens; SKILL.md has 848 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~27
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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 ntorga/agent-starter-kit at commit 851e942, republished under its MIT licence (© ntorga). 848 words, ~1,750 tokens.

Download SKILL.mdSave it as .claude/skills/plan-management/SKILL.md (or your agent's skills folder).
name
plan-management
description
Plan lifecycle — grill entry point, grounding, artifact review, per-epic execution, revision.
usedBy
maestro
version
3.0.3
lastUpdated
2026-09-12

Purpose

This skill defines everything about plans: when to grill, how to ground and review the plan artifacts, how to execute epics, and how to revise. Read this skill whenever the task may require a plan.

Procedure

Plans live in a directory under .memory/plan/:

.memory/plan/<feature-slug>/
├── tree.md    — the design tree: decisions, dependencies, recommendations, impact
├── plan.md    — acceptance criteria, what + why only
├── arch.md    — directory structure, layer separation, reference projects
└── impl.md    — epics grouped at one day of work, grounded with file paths, method signatures, test specs
  • <feature-slug> — short kebab-case summary of the feature.
  • tree.md — the grill's working state. The Architect builds and extends it. All nodes settled when the grill terminates.
  • plan.md — acceptance criteria from the settled business decisions. Living document, edited inline as understanding evolves.
  • arch.md — directory structure, layer separation, reference projects. Produced during the grill. The beginner path gets defaults from the maintenance, lightweight, and safe principles (KISS, single responsibility, safe boundaries — rules/code/general.md).
  • impl.md — epics grouped at one day of work. The grill transcribes them. The Architect grounds and re-grounds them. Living document, edited inline as epics land.

Epic completion tracking: Epics in impl.md are annotated with ✓ when fully delivered, or ~ when partially delivered. All epics marked ✓ means the feature is complete.

Parallelizable groups: impl.md notes which epics can run in parallel. The Maestro may dispatch parallel epics to separate coders when file scopes do not overlap (follows: skills/dispatch/SKILL.md).

Deciding When to Plan

A plan is required when the request is lengthy, multi-part, or describes a non-trivial change. When in doubt, plan — planning a simple task wastes minutes; skipping a plan on a complex task wastes hours.

If the task does not warrant a full plan, create a to-do instead (uses: skills/task-tracking/SKILL.md).

Grilling

For tasks requiring a plan:

  1. Run the grill. Read and follow skills/grill/SKILL.md.
  2. Confirm. Present the artifacts to the user. Do not act until the user confirms shared understanding.
Grounding

After the user confirms:

  1. Dispatch the Architect (personas/architect.md) (follows: skills/dispatch/SKILL.md) in ground mode. The Architect reads plan.md, arch.md, and impl.md, then annotates impl.md per skills/architect-impl-grounding/SKILL.md.
  2. If the Architect returns escalations (facts that contradict settled decisions), present them to the user. Do not proceed until the user resolves them.
Artifact Review Gate

After grounding:

  1. Send the grounded artifacts through the review loop (follows: skills/review-loop/SKILL.md) before proceeding to implementation.
  2. If the review verdict is fail, re-dispatch the Architect (personas/architect.md) (follows: skills/dispatch/SKILL.md) with the confirmed findings — plan revision for plan.md or arch.md defects, grounding revision for impl.md defects — and re-review.
  3. Proceed to implementation only when the artifacts pass (pass or partial-pass).
Tracking Progress

For each pending epic, in order:

  1. Refresh (skip for the first epic after initial grounding). Dispatch the Architect (personas/architect.md) (follows: skills/dispatch/SKILL.md) in refresh mode. The Architect classifies the landed epic's discoveries (adjust or escalate) and re-grounds the next epic against the current codebase.
  2. Escalations. If the Architect flagged escalations, present them to the user. Do not proceed until the user resolves them.
  3. Dispatch the Coder (personas/coder.md) (follows: skills/dispatch/SKILL.md) for the current epic. One epic per dispatch.
  4. Review loop. Read and follow skills/review-loop/SKILL.md on the epic's code.
  5. Mark the epic in impl.md with ✓ (fully delivered) or ~ (partially delivered).

If all epics are marked ✓, the feature is complete. Before reporting to the user, run the review loop in full branch mode (follows: skills/review-loop/SKILL.md → step 1) to comprehensively review the entire branch's accumulated changes.

Show full SKILL.md (323 more words)Show less
Finding Plans

To find the plan for a feature:

bash
ls .memory/plan/<feature-slug>/

The directory contains tree.md, plan.md, arch.md, and impl.md. If the directory does not exist, no plan exists for that feature.

To find all features with plans:

bash
ls -d .memory/plan/*/
Reading Plans Efficiently
  1. Find the plan directory. Run ls .memory/plan/<feature-slug>/.
  2. Read plan.md. See all acceptance criteria and which are delivered (✓), partially delivered (~), or pending.
  3. Read impl.md. See all epics, which are delivered (✓), partially delivered (~), or pending, and the annotated file paths and method signatures.
  4. Read arch.md only when revising architecture. Read tree.md only when re-grilling or resuming a mid-grill session.
Revising Plans

When plan revision is needed (new discoveries, clarified requirements):

  1. Edit plan.md or impl.md inline. The artifacts are living documents. Never version-bump them.
  2. If the revision touches epics, re-dispatch the Architect (personas/architect.md) (follows: skills/dispatch/SKILL.md) to re-ground the affected epics.
  3. Send the revised artifacts through the review loop (follows: skills/review-loop/SKILL.md).

When an epic needs revision (feedback after implementation):

  1. Assess the feedback. If the feedback requires only minor fixes (typos, small code corrections, no structural impact), dispatch the Coder (personas/coder.md) (follows: skills/dispatch/SKILL.md) directly to fix. If the feedback involves structural changes or scope changes, proceed to step 2.
  2. Edit impl.md inline. Update the epic with the revised scope. Re-dispatch the Architect (personas/architect.md) (follows: skills/dispatch/SKILL.md) to re-ground the affected epic. Send the revised artifacts through the review loop.

Guardrails

  • Never mark an epic complete that has not passed the review loop.
  • Never version-bump the plan artifacts. Edit them inline.
  • When resuming, never bulk-read the plan directory — read plan.md, then impl.md for current progress. Read arch.md and tree.md only when their sections say to.
  • Never dispatch the Coder on an epic whose grounding is stale after a landed epic — refresh first.
  • If plan files cannot be found, stop and report the error. Do not guess paths.
  • Never proceed to the next epic when escalations are unresolved. The user must resolve them first.

© ntorga, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/plan-management of ntorga/agent-starter-kit.

Open the folder on GitHubat commit 851e942

Compare with similar skills

Plan Management 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.

Plan Management compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Plan Management this skillntorga/agent-starter-kit146—~1.8kAutomated safety check: PassMIT
Agent BuildershareAI-lab/learn-claude-code78k6 repos~1.2kAutomated safety check: PassMIT
Planning With Filesjarrodwatts/claude-code-config1.1k5 repos~967Automated safety check: PassNone
Codebase Managementgiancarloerra/SocratiCode3.3k1 repos~1.8kAutomated safety check: PassAGPL-3.0
Context Compressionguanyang/open-agent-hub9732 repos~4.6kAutomated safety check: PassMIT
Looperksimback/looper710—~2.7kAutomated safety check: NotesMIT

Similar skills

  • Agent Builder

    shareAI-lab/learn-claude-code

    Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code.

    78k GitHub starsUsed in 6 repos~1.2k tokens
    AI & LLM EngineeringAuto-check passed

  • Planning With Files

    jarrodwatts/claude-code-config

    Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage.

    1.1k GitHub starsUsed in 5 repos~967 tokens
    AI & LLM EngineeringAuto-check passed

  • Codebase Management

    giancarloerra/SocratiCode

    Set up, index, and manage SocratiCode codebase indexing. An agent skill from giancarloerra/SocratiCode.

    3.3k GitHub starsUsed in 1 repo~1.8k tokens
    AI & LLM EngineeringAuto-check passed

  • Context Compression

    guanyang/open-agent-hub

    This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve…

    973 GitHub starsUsed in 2 repos~4.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Looper

    ksimback/looper

    Scaffold a well-designed agent loop with best-practice coaching and a cross-model review council.

    710 GitHub stars~2.7k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check: notes

  • Docs Planner

    strands-agents/harness-sdk

    Identify documentation gaps and prioritize the docs backlog.

    8.7k GitHub stars~821 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

More from ntorga/agent-starter-kit

All 21 skills in this repo

  • Agent Decision

    ntorga/agent-starter-kit

    Deterministic self-evaluation rubric for decision escalations — scored every run using the FRAME framework.

    146 GitHub stars~1.7k tokensUpdated 25 days ago
    Auto-check passed

  • Agent Memory

    ntorga/agent-starter-kit

    Long-term and session memory across sessions. An agent skill from ntorga/agent-starter-kit.

    146 GitHub stars~2.7k tokensUpdated 25 days ago
    Auto-check passed

  • Architect Design Tree

    ntorga/agent-starter-kit

    Builds the design tree for the grill — decisions mapped as nodes with dependencies, recommendations, and impact, pruned by path.

    146 GitHub stars~1.2k tokensUpdated 25 days ago
    Auto-check passed

  • Architect Impl Grounding

    ntorga/agent-starter-kit

    Grounds the grill's settled decisions in the codebase — annotates impl.md with file paths, signatures, reference files, test specs, and LOC; re-grounds the next epic after each landing.

    146 GitHub stars~944 tokensUpdated 25 days ago
    Auto-check passed

  • Boot

    ntorga/agent-starter-kit

    Session startup — gitignore, auto-update, memory, rules, context, CLI config, and greet.

    146 GitHub stars~937 tokensUpdated 25 days ago
    Auto-check passed

  • Browser Inspect

    ntorga/agent-starter-kit

    Browser inspection and interaction for verifying rendered web UI during development.

    146 GitHub stars~2k tokensUpdated 25 days ago
    Auto-check passed

Categories

Questions about Plan Management

What does Plan Management do?

Plan lifecycle — grill entry point, grounding, artifact review, per-epic execution, revision. Plan Management is an agent skill from ntorga/agent-starter-kit. Plan lifecycle — grill entry point, grounding, artifact review, per-epic execution, revision.

When should I use Plan Management?

Plan Management fits situations like: AI & LLM Engineering work in your project.

How do I install Plan Management in Claude Code?

Run `npx skills add ntorga/agent-starter-kit --skill plan-management -a claude-code`. Or copy the skill folder (skills/plan-management in ntorga/agent-starter-kit) into .claude/skills/plan-management in your project. Claude Code loads it when a task matches its description.

How do I install Plan Management in Codex?

Run `npx skills add ntorga/agent-starter-kit --skill plan-management -a codex`. Or copy the skill folder (skills/plan-management in ntorga/agent-starter-kit) into .agents/skills/plan-management in your project. Codex loads it when a task matches its description.

Can I use Plan Management 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 ntorga/agent-starter-kit --skill plan-management -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/plan-management, .gemini/skills/plan-management, .github/skills/plan-management and .opencode/skills/plan-management in your project.

What does Plan Management need to run?

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

Does Plan Management 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 Plan Management 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 Plan Management use?

Plan Management 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 Plan Management use?

About 1.8k tokens (SKILL.md is roughly 7k 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 Plan Management?

Skills that share tags, products or a category with Plan Management: Agent Builder (shareAI-lab/learn-claude-code, 78k stars), Planning With Files (jarrodwatts/claude-code-config, 1.1k stars), Codebase Management (giancarloerra/SocratiCode, 3.3k stars) and Context Compression (guanyang/open-agent-hub, 973 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Plan Management?

ntorga (a GitHub user) maintains it in ntorga/agent-starter-kit, which has 146 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on September 12, 2026.

Source: ntorga/agent-starter-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.