execute

A workflow for carrying out an existing software plan one step at a time on its own Git branch. It checks the work after each step, performs a deeper final review, and records progress in a dated journal.

In plain words
What is it for?
Use it to execute plans stored in files such as plan.md, design.md, or prd.md, run tests and linting, fix failures, test for unexpected problems, and prepare traceable changes.
Why use it?
It reduces the chance that a long implementation drifts from its plan or leaves failures unnoticed. The journal connects decisions, checks, fixes, and commits in one record.

Skill for Claude CodeCodex

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/abilenduke/copilot-developer/execute
Any agent
npx skills add ABilenduke/copilot-developer --skill execute
Clone the repo
git clone --depth 1 https://github.com/ABilenduke/copilot-developer

Made for: Claude Code, Codex.

Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,737 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 $0.00109 $0.05737
Opus 5 $0.00055 $0.02868
Sonnet 5 $0.00022 $0.01147
Haiku 4.5 $0.00011 $0.00574

Measured yesterday against content hash 458e2af70b67, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

execute 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 yesterday.

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.

.claude/skills/execute/SKILL.md · 606 lines

How it starts

The opening of the file, as written. The whole thing — 606 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Executor Skill

Purpose

This skill takes a plan created by /plan and works through it step by step on a dedicated git branch. It uses a two-tier verification system:

  • Per-step ralph loops (fast) — run relevant tests and lint after each step, fix failures iteratively
  • Final ralph loop (deep) — a structured multi-phase review that goes beyond "do tests pass" into self-review, adversarial testing, and acceptance verification

A companion journal records everything — implementation details, verification results, fixes, and commit hashes.

First Steps

When this skill is invoked:

  1. Read templates/journal-template.md to understand the journal format
  2. Read examples/example-journal.md to see the expected quality
  3. Locate the plan:
    • If the user specified a path, use that
    • If not, check docs/features/ for available plans. Show what exists and ask which to execute.
    • If no plans exist, tell the user to run /plan first.
  4. Detect format (see Format Detection below)
  5. Run the Definition of Ready gate (see Definition of Ready below)
  6. Read all available story documents thoroughly. Understand every step AND every acceptance criterion.
  7. Identify verification stack: Examine the project to determine what's available:
    • Test runner (e.g. php artisan test, npm test, pytest)
    • Linter (e.g. phpstan, eslint, pint, ruff)
    • Type checker (e.g. vue-tsc, tsc --noEmit, mypy)
    • Any custom checks mentioned in the plan
    • Record these in the journal header as the verification stack
  8. Set up the git branch (see Git Workflow below)
  9. Update GitHub ticket status (new format only — see GitHub Integration below)
  10. Create the journal file alongside the plan
  11. Write the journal header (including "Documents available" status)
  12. Begin executing Step 1

Format Detection

Detect whether this is the new multi-file story format or the old monolithic iteration format:

Read the full file on GitHub · 606 lines

Files

What ships with it

2 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. yesterday First seen · 606 lines · 109 tokens per session scan A 458e2af70b67

Subscribe to this mod's changes

execute is a skill published in the GitHub repository ABilenduke/copilot-developer (4 stars, last pushed 6mo ago), licensed MIT. It adds 109 tokens to every session and 5,737 once invoked, about $0.0005 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.

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

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens