execute-plan

execute-plan is a skill for Claude Code, Codex from syou6162/agent-skills. It costs 57 tokens per session (840 once invoked), scanned A, original, MIT.

A process for starting implementation from the newest saved work plan. It turns the plan's execution steps into tasks, completes them in order, creates a commit for each task, and finishes with a review.

In plain words
What is it for?
Use it to carry out a coding plan step by step, track completion, commit each meaningful change, and run a final code review.
Why use it?
It prevents implementation from starting without a plan and reduces the chance of leaving planned work unfinished.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Codex.

Good fit Use it to carry out a coding plan step by step, track completion, commit each meaningful change, and run a final code review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/syou6162/agent-skills/execute-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 syou6162/agent-skills --skill execute-plan
Clone the repo
git clone --depth 1 https://github.com/syou6162/agent-skills

Made for: Claude Code, Codex.

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 execute-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/syou6162/agent-skills/execute-plan.svg)](https://agentmods.dev/skills/syou6162/agent-skills/execute-plan)
Your own site
<a href="https://agentmods.dev/skills/syou6162/agent-skills/execute-plan"><img src="https://agentmods.dev/badge/skills/syou6162/agent-skills/execute-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 840 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00057 $0.00840
Opus 5 $0.00028 $0.00420
Sonnet 5 $0.00011 $0.00168
Haiku 4.5 $0.00006 $0.00084

Measured 8d ago against content hash 3620a17a7add, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

execute-plan scanned grade A with 0 findings 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 8d ago.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/execute-plan/SKILL.md · 72 lines

What it actually says

planモードから実装開始

planモードで作成した計画に基づいて実装を開始します。planファイルの内容を読み取り、タスクリストを作成し、各タスクを順次実行していきます。

  • 本スキルでの「planモード」はClaude Code固有の機能です。Planモードが存在しないエージェント環境では、「計画フェーズ」として読み替えてください。

禁止事項

  • タスクを完了せずに勝手に終了しない
  • すべてのタスクが完了するまで必ず作業を続ける
  • planファイルが存在しない場合は実装を開始しない

実行手順

1. planファイルの特定

.claude_work/plans/ ディレクトリ内のplanファイルを特定します。

ls -t .claude_work/plans/*.md | head -n 1
  • 最終更新日が最も新しいファイルを使用(ls -t で降順ソート、head -n 1 で最新の1ファイルを取得)
  • ファイルが存在しない場合: ユーザーに報告して終了

2. planファイルの読み取り

特定したplanファイルをReadツールで読み取ります。

3. タスクリストの作成

planファイルの「実行計画」セクションから各ステップを抽出し、タスクリストを作成します(Claude CodeではTaskCreateツール、他のエージェントでは同等のタスク管理機能を使用)。

各タスクは以下の形式で作成してください:

  • subject: ステップのタイトル(簡潔に)
  • description: ステップの詳細内容
  • activeForm: 「〜を実行中」形式

最後に「Codex レビューを実行」タスクを追加します。

4. タスクの順次実行

タスクリストの順番に従って、各タスクを実行します。

各タスクについて:

  1. タスクを in_progress に更新(Claude CodeではTaskUpdateツール、他のエージェントでは同等のタスク管理機能を使用)
  2. タスクの内容を実行
  3. タスクを completed に更新
  4. タスクの変更をコミット作成(git addgit commit でタスク単位の意味のあるコミットメッセージを付ける)

5. 最終レビュー

すべての実装タスクが完了したら、最後にcodex-reviewスキルを実行します(Claude Codeでは Skill(syou6162-agent-skills:codex-review))。

注意事項

  • このスキルはオーケストレーションが役割です。実装そのものはメインエージェントが行います。
  • 各タスク完了時に必ずコミットを作成してください。
  • すべてのタスクが完了するまで作業を続けてください。
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. 8d ago First seen · 72 lines · 0 tokens per session scan A 3620a17a7add

Subscribe to this mod's changes

execute-plan is a skill published in the GitHub repository syou6162/agent-skills (11 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 840 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.