executing-plans · mdiri-ai — Claude Code skill: setup and use
executing-plans is a Claude Code skill that carries out written implementation plans with review checkpoints. It pauses when a blocker needs clarification.
MIT ★ 6,467 updated 2026-11-16
npx skills add mdiri-ai/SoduWork --skill executing-plans -a claude-codeWhat executing-plans does
executing-plans loads an implementation plan, checks its logic, and turns its items into an ordered task list. It works through each step, runs the verifications named by the plan, and marks the work as it progresses.
The SoduWork workflow starts with SODUWORK.md, which must be read first. Execution pauses for a missing dependency, a failed check, a serious gap in the plan, or an unclear instruction. Once all tasks are verified, the skill hands off to finishing-a-development-branch; when subagents are available, it points to subagent-driven-development instead.
What it helps with
- review a written implementation plan before coding
- turn plan items into an ordered task list
- run the checks attached to each task
- pause on blockers instead of guessing
- keep implementation off
mainormasterwithout consent
Example prompts for the agent
- Execute the plan in
implementation-plan.mdand verify each task. - Review this plan, create the task list, and stop if it has a critical gap.
- Work through the plan in an isolated workspace, checking every step.
How to install executing-plans
1Skills CLI (Vercel)
npx skills add mdiri-ai/SoduWork --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 mdiri-ai/SoduWork --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 mdiri-ai/SoduWork --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 mdiri-ai/SoduWork skills/executing-plans2Manually: put the files in place
.github/skills/executing-plans/SKILL.md1Skills CLI (Vercel)
npx skills add mdiri-ai/SoduWork --skill executing-plans -a gemini-cli2Platform CLI
gemini skills install https://github.com/mdiri-ai/SoduWork --path 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 mdiri-ai/SoduWork --skill executing-plans -a claude-code. The skill file will be placed at ~/.claude/skills/executing-plans/SKILL.md.
What does executing-plans do?
It reads a written plan, reviews it before implementation, tracks its tasks, and runs the listed checks as work proceeds. After completion, it invokes finishing-a-development-branch.
What happens when a plan or verification is blocked?
The skill stops when it encounters a missing dependency, failed verification, a critical plan gap, or an unclear instruction. The agent asks for clarification instead of guessing.
Source text
SKILL.md · MIT
--- name: executing-plans description: Use when you have a written implementation plan to execute in a separate session with review checkpoints --- Before following the upstream workflow in SoduWork, read [SoduWork runtime adaptation](SODUWORK.md). # Executing Plans ## Overview Load plan, review critically, execute all tasks, report when complete. **Announce at start:** "I'm using the executing-plans skill to implement this plan." **Note:** Tell your human partner that Superpowers works much better with access to subagents (Claude Code, Codex CLI, Codex App, Copilot CLI, and Gemini CLI all qualify; see the per-platform tool refs in `../using-superpowers/references/`). If subagents are available, use superpowers:subagent-driven-development instead of this skill. ## The Process ### Step 1: Load and Review Plan 1. Ensure an isolated workspace: use superpowers:using-git-worktrees to create one or verify the existing one 2. Read plan file 3. Review critically - identify any questions or concerns about the plan 4. If concerns: Raise them with your human partner before starting 5. If no concerns: Create todos for the plan items and proceed ### Step 2: Execute Tasks For each task: 1. Mark as in_progress 2. Follow each step exactly (plan has bite-sized steps) 3. Run verifications as specified 4. Mark as completed ### Step 3: Complete Development After all tasks complete and verified: - Announce: "I'm using the finishing-a-development-branch skill to complete this work." - **REQUIRED SUB-SKILL:** Use superpowers:finishing-a-development-branch - Follow that skill to verify tests, present options, execute choice ## When to Stop and Ask for Help **STOP executing immediately when:** - Hit a blocker (missing dependency, test fails, instruction unclear) - Plan has critical gaps preventing starting - You don't understand an instruction - Verification fails repeatedly **Ask for clarification rather than guessing.** ## When to Revisit Earlier Steps **Return to Review (Step 1) when:** - Partner updates the plan based on your feedback - Fundamental approach needs rethinking **Don't force through blockers** - stop and ask. ## Remember - Review plan critically first - Follow plan steps exactly - Don't skip verifications - Reference skills when plan says to - Stop when blocked, don't guess - Never start implementation on main/master branch without explicit user consent
© mdiri-ai · MIT · mdiri-ai/SoduWork
Similar skills
All skills for Agent setup: memory, context, orchestration →executing-plans by other authors comes first.