executing-plans · dev-toolings — Claude Code skill: plan execution
The executing-plans skill guides Claude Code through an approved implementation plan, with test-first steps and a separate commit for each one. Use it for multi-step work or to resume after an interruption.
MIT ★ 234 updated 2026-10-05
npx skills add dev-toolings/superpowers-symfony --skill executing-plans -a claude-codeWhat executing-plans does
The workflow starts by reading the full plan, checking that baseline tests pass, and working on a branch. For each step, the skill calls for writing a test and seeing it fail before implementing the change; then the test must pass before refactoring. Each finished step gets its own commit.
At the end of a phase, run style checks, static analysis, and the full test suite. Record each step’s status in the plan. If the work no longer matches the plan, stop and report the deviation instead of changing the plan silently. A separate reference.md file holds deeper implementation details, so this skill sets the execution process rather than supplying project-specific technical guidance.
What it helps with
- check the test baseline before implementation
- split a plan into steps with separate commits
- verify that a test fails before changing the code
- record step status and explain deviations
Example prompts for the agent
- Carry out the approved implementation plan one step at a time, testing before and after each change.
- Resume the plan after an interruption and update the status of every step.
- Compare the current work with the plan and report any deviation.
How to install executing-plans
1Skills CLI (Vercel)
npx skills add dev-toolings/superpowers-symfony --skill executing-plans -a claude-code2Manually: put the files in place
~/.claude/skills/executing-plans/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/executing-plans/
1Skills CLI (Vercel)
npx skills add dev-toolings/superpowers-symfony --skill executing-plans -a codex2Manually: put the files in place
.agents/skills/executing-plans/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add dev-toolings/superpowers-symfony --skill executing-plans -a cursor2Manually: put the files in place
.cursor/skills/executing-plans/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install dev-toolings/superpowers-symfony content/skills/executing-plans2Manually: put the files in place
.github/skills/executing-plans/SKILL.md1Skills CLI (Vercel)
npx skills add dev-toolings/superpowers-symfony --skill executing-plans -a gemini-cli2Platform CLI
gemini skills install https://github.com/dev-toolings/superpowers-symfony --path content/skills/executing-plansManually: put the files in place
.devin/skills/executing-plans/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about executing-plans
How do I install executing-plans in Claude Code?
Run npx skills add dev-toolings/superpowers-symfony --skill executing-plans -a claude-code. The skill file is installed at ~/.claude/skills/executing-plans/SKILL.md.
What does executing-plans do?
It guides implementation through an approved plan: test a step first, make the change, verify it, then commit that step on its own. It also calls for quality checks at the end of each phase and status updates in the plan.
What happens when implementation diverges from the plan?
The workflow says to stop and report the deviation and its reason rather than silently altering the plan. For a blocker, fix its cause instead of changing the test.
Source text
SKILL.md · MIT
--- name: executing-plans description: Methodically execute implementation plans with a TDD approach, incremental commits, and continuous validation capabilities: [read, search, edit, shell] tags: [workflow] # projected by `bun run build` — do not edit by hand allowed-tools: - Read - Glob - Grep - Write - Edit - Bash --- # Executing Plans (Symfony) ## Use when - An approved implementation plan exists and must be carried out. - The work spans several steps that must each land green. - Resuming a plan after an interruption or a blocker. ## Default workflow 1. Read the whole plan, confirm the baseline tests pass, and work on a branch. 2. For each step, write the test, watch it fail, implement, watch it pass, then refactor. 3. Commit after each completed step, with a message that names it. 4. Run the quality gates (style, static analysis, full suite) at the end of each phase. 5. Track each step's status in the plan, and stop to report when reality contradicts it. ## Guardrails - Never skip watching the test fail: a test that never failed proves nothing. - One step per commit; do not batch steps. - Do not change the plan silently: report the deviation and the reason. - On a blocker (failing migration, autowiring error), fix the cause, not the test. ## Progressive disclosure - Use this file for execution posture and risk controls. - Open references when deep implementation details are needed. ## Output contract - One commit per step, tests included. - The plan with the status of every step. - Final validation results and any deviation from the plan. ## References - `reference.md`
© dev-toolings · MIT · dev-toolings/superpowers-symfony
Similar skills
All skills for Testing and QA →executing-plans by other authors comes first.