plan-execution

plan-execution is a skill for Claude Code, Codex from aquivalabs/speccy. It costs 36 tokens per session (2,768 once invoked), scanned A, original, MIT.

A workflow for breaking an approved implementation plan into manageable coding tasks and having agents execute them. It also brings the completed work together and checks that the plan is complete.

In plain words
What is it for?
Use it to carry out multi-step development plans. It can run sequential work in the main checkout and isolate parallel work in Git worktrees before merging it back.
Why use it?
It reduces the risk of oversized tasks, missed steps, conflicting edits, or unverified changes.

Skill for Claude CodeCodex

Part of the speccy plugin — 2 skills 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 skills/aquivalabs/speccy/plan-execution
Any agent
npx skills add aquivalabs/speccy --skill plan-execution
Clone the repo
git clone --depth 1 https://github.com/aquivalabs/speccy

Made for: Claude Code, Codex.

Or install speccy, the plugin that ships this one along with the rest of its 2 skills.

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 plan-execution

README.md
[![agentmods](https://agentmods.dev/badge/skills/aquivalabs/speccy/plan-execution.svg)](https://agentmods.dev/skills/aquivalabs/speccy/plan-execution)
Your own site
<a href="https://agentmods.dev/skills/aquivalabs/speccy/plan-execution"><img src="https://agentmods.dev/badge/skills/aquivalabs/speccy/plan-execution.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,768 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 $0.00036 $0.02768
Opus 5 $0.00018 $0.01384
Sonnet 5 $0.00007 $0.00554
Haiku 4.5 $0.00004 $0.00277

Measured 4d ago against content hash 2b17ff507aa3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-execution 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 4d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (workflow-simple.js, workflow.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/plan-execution/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Execution

Break an approved plan into tasks sized for a single agent context window, then execute them as subagents. Sequential tasks run directly on the main checkout; parallel tasks use git worktrees for isolation and are squash-merged back afterward.

If the plan fits a single context window, still use this skill: it produces one task and executes directly.

Prerequisites

Verification tools

Check that CLAUDE.md documents the project's verification tools (build, lint, static analysis, test commands). Execute agents rely on these to validate their work. If they're missing, tell the user: establishing verification standards comes before running a plan.

Worktree init

Worktree init is only needed when the plan has parallel tasks (which use git worktrees). If the plan is purely sequential, skip this section.

Worktrees must branch from the current HEAD so that parallel tasks see work committed by prior sequential tasks. Check .claude/settings.json for "worktree": { "baseRef": "head" }. If missing, add it (via Bash/python, since direct Edit on that file is blocked). The default (fresh) branches from origin/<default-branch>, which misses all feature-branch commits.

Check whether CLAUDE.md has a ## Worktree init section. If it does, resolve the gather/apply variables before running the workflow:

  1. Parse the Gather block, where each line has the form NAMEcommand. Run each command via Bash in the main checkout and capture its stdout (trimmed).
  2. Parse the Apply block, where each line is a shell command that may reference ${NAME} variables from the gather step. Substitute the gathered values into each command. Make symlink commands idempotent: replace ln -s with ln -snf so re-runs don't create circular symlinks inside the existing target.
  3. Pass the resolved commands as the worktreeInit arg (string array) to the workflow.

If the section is missing and the plan has parallel tasks, tell the user. Worktree agents without init commands will lack gitignored state, which causes build failures, missing configs, and mid-task recovery friction. Offer to help draft the section before proceeding, the same way you would for missing verification tools.

Read the full file on GitHub · 120 lines

Files

What ships with it

5 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. 4d ago First seen · 120 lines · 36 tokens per session scan A 2b17ff507aa3

Subscribe to this mod's changes

plan-execution is a skill published in the GitHub repository aquivalabs/speccy (11 stars, last pushed 7d ago), licensed MIT. It adds 36 tokens to every session and 2,768 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens