execute-plan

execute-plan is a command for coding agents from muhimu/claude-plan-lifecycle. It costs 84 tokens per session (5,536 once invoked), scanned A, original, MIT.

A command that carries out a repository plan from start to finish in a separate Git worktree, a linked checkout for isolated changes.

In plain words
What is it for?
Executing planned work, running the required tests or lint checks, creating stacked draft pull requests, and updating plan metadata.
Why use it?
It coordinates implementation, verification, commits, pushing, a draft pull request, and recording the resulting PR number in the plan.

Command

Part of the plan-lifecycle plugin — 3 skills, 4 commands shipped together

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.

agentmods
npx agentmods add commands/muhimu/claude-plan-lifecycle/execute-plan
Clone the repo
git clone --depth 1 https://github.com/muhimu/claude-plan-lifecycle

Or install plan-lifecycle, the plugin that ships this one along with the rest of its 3 skills, 4 commands.

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/commands/muhimu/claude-plan-lifecycle/execute-plan.svg)](https://agentmods.dev/commands/muhimu/claude-plan-lifecycle/execute-plan)
Your own site
<a href="https://agentmods.dev/commands/muhimu/claude-plan-lifecycle/execute-plan"><img src="https://agentmods.dev/badge/commands/muhimu/claude-plan-lifecycle/execute-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,536 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00084 $0.05536
Opus 5 $0.00042 $0.02768
Sonnet 5 $0.00017 $0.01107
Haiku 4.5 $0.00008 $0.00554

Measured 3d ago against content hash 286061a26841, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

commands/execute-plan.md · 374 lines

How it starts

The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execute Plan

Drive one plan from the plans dir end-to-end in the current worktree: invoke the chosen execution skill (superpowers:subagent-driven-development or superpowers:executing-plans) against it, verify (test/lint per the verify convention), commit and push, open a draft PR, and stamp the plan file with the PR number.

This command runs in a dedicated git worktree (created by your worktree manager of choice or plain git worktree add). It refuses to run in the main checkout.

Step 1 — Pre-flight checks

Run each check in order. On any failure, stop: print the message and end the turn.

  1. Inside a git worktree?

    git rev-parse --is-inside-work-tree
    

    If not, stop: "Not inside a git working tree."

  2. Worktree, not main checkout?

    git rev-parse --git-dir
    

    If output is .git (or an absolute path ending in /.git), this is the main checkout, not a worktree. Stop: "This command refuses to run in the main checkout. Create a worktree (git worktree add or your worktree manager) and run it there."

    If output contains .git/worktrees/<name>, you're in a worktree. Continue.

  3. Branch is not the default branch? Resolve the repo's default branch once — every later mention of $DEFAULT_BRANCH in this command means this value:

    DEFAULT_BRANCH="$(git symbolic-ref --short refs/remotes/origin/HEAD 2>/dev/null | sed 's|^origin/||')"
    [ -n "$DEFAULT_BRANCH" ] || DEFAULT_BRANCH="$(gh repo view --json defaultBranchRef -q .defaultBranchRef.name)"
    git rev-parse --abbrev-ref HEAD
    

    If the current branch is $DEFAULT_BRANCH (or main/master), stop: "Worktree is on a protected branch. Switch to a feature branch first."

  4. Tree state:

    git status --porcelain
    

    If non-empty, warn ("Worktree has uncommitted changes — executing-plans will likely commit them as part of execution") but continue.

  5. Execution skills available? This command drives plans via the superpowers plugin. If neither superpowers:executing-plans nor superpowers:subagent-driven-development appears in the available-skills list, stop: "The superpowers plugin is required (https://github.com/obra/superpowers). Install it and re-run."

Read the full file on GitHub · 374 lines

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. 3d ago First seen · 374 lines · 84 tokens per session scan A 286061a26841

Subscribe to this mod's changes

execute-plan is a command published in the GitHub repository muhimu/claude-plan-lifecycle (2 stars, last pushed 7d ago), licensed MIT. It adds 84 tokens to every session and 5,536 once invoked, about $0.0004 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 2026-08-31.