implement-plan

implement-plan is a skill for Claude Code from patrickdappollonio/claude-plugins. It costs 81 tokens per session (7,857 once invoked), scanned C, original, MIT.

A procedure for carrying out an agreed software plan and turning it into reviewed, tested, documented code. It can split a large job among separate working copies and helper agents.

In plain words
What is it for?
It helps implement multi-step coding plans, divide work across agents, review each part, run tests, update related documentation, and fix problems found during review.
Why use it?
It keeps implementation tied to the decisions already made and checks the result against the plan. This reduces missed requirements and unfinished cleanup.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

Part of the implement-plan plugin — 1 skill shipped together

Good fit It helps implement multi-step coding plans, divide work across agents, review each part, run tests, update related documentation, and fix problems found during review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/patrickdappollonio/claude-plugins/implement-plan
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add patrickdappollonio/claude-plugins --skill implement-plan
Clone the repo
git clone --depth 1 https://github.com/patrickdappollonio/claude-plugins

Made for: Claude Code.

Or install implement-plan, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for implement-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/patrickdappollonio/claude-plugins/implement-plan/github.svg)](https://agentmods.dev/skills/patrickdappollonio/claude-plugins/implement-plan)
Your own site
<a href="https://agentmods.dev/skills/patrickdappollonio/claude-plugins/implement-plan"><img src="https://agentmods.dev/badge/skills/patrickdappollonio/claude-plugins/implement-plan/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for implement-plan

Your own site · 80×15
<a href="https://agentmods.dev/skills/patrickdappollonio/claude-plugins/implement-plan"><img src="https://agentmods.dev/badge/skills/patrickdappollonio/claude-plugins/implement-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,857 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00081 $0.07857
Opus 5 $0.00041 $0.03929
Sonnet 5 $0.00016 $0.01571
Haiku 4.5 $0.00008 $0.00786

Measured today against content hash d8f107860f1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

implement-plan scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Any `git worktree remove`, `git branch -d/-D`, or `rm -rf` of a worktree before the G4 answer
plugins/implement-plan/skills/implement-plan/SKILL.md · 476 lines

How it starts

The opening of the file, as written. The whole thing — 476 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement Plan

Overview

Turn an agreed plan into merged, reviewed, tested, documented code — hands-free where possible, and never deciding for the user what is theirs to decide. The orchestrator (you) plans the split, dispatches executors, checks their work against the plan thoroughly, runs an adversarial review, fixes what it finds, cleans up the comments and the shape of the code it merged, and keeps going until the plan is done.

The executor discipline in this skill (minimum sufficient change, the four-line mini-plan, pause-and-confirm, "done means") is adapted from @voxyz_ai. The orchestration around it — worktrees, conformance review, adversarial review, model routing, capacity, the keep-going contract — is this skill's own.

Three rules bind everything below:

  1. The plan is the spec. Work is measured against what was agreed, item by item — never against "does it look right".
  2. Technical direction is yours; operational and functional direction is the user's. Never assume for them. The table under Two Authorities decides which is which.
  3. Keep going. Stop only at the named gates, and when you stop, make the resume a single word.

Read the Companion Files First

This skill ships in two layers. SKILL.md carries the rules and a summary of each step; six files beside it carry the full procedures:

  • handoff-packet.md — the executor prompt: scope, TDD, the test map, the documentation rule, user-journey tests, the executor discipline, stop conditions
  • conformance-review.md — the thorough plan-vs-work check, item by item
  • adversarial-review-fallback.md — how to run the installed review skills, the plan-as-diff variant, and the on-the-spot panel when no skill is installed
  • model-routing.md — which model executes, which judges, and the trade you must state
  • capacity-check.md — the back-of-the-napkin estimate, the advisory usage check, /goal, and the resume line
  • companion-skills.md — the skills this one uses when installed (adversarial-review, adversarial-review-quick, visual-plan, appropriate-comments-code, code-simplification, use-premium-models-efficiently, use-claude-limits-efficiently), what each adds, and how to install them on Claude Code, Codex, or via npx skills

Read the full file on GitHub · 476 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today Changed · +11 lines d8f107860f1e
  2. yesterday Changed · +59 lines b8166cecaec8
  3. 6d ago First seen · 406 lines · 81 tokens per session scan C 29bb8e0e15fe

Subscribe to this mod's changes

implement-plan is a skill published in the GitHub repository patrickdappollonio/claude-plugins (8 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 7,857 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.