agentleFS
hdprajwalhdprajwal/agent-skills/skills/executing-plans/SKILL.md

executing-plans

Skill1 starsChanged 5 months agoMITView on GitHub

Run a written plan inline in the current session with review checkpoints: load it, review it critically, run each task exactly with its verifications, prove it actually runs, then finish on a branch → PR → merge. Use when you have a plan from writing-plans and tasks are coupled enough to keep in one session. Stops and asks when blocked.

  • Commits and pushes

189 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use chinese-code-review, chinese-commit-conventions and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Leodorareluctant259Skill

    chinese-code-review

    中文代码审查规范——在保持专业严谨的同时,用符合国内团队文化的方式给出有效反馈

    Also in 8 projects that use this

  • Leodorareluctant259Skill

    chinese-commit-conventions

    中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化

    Also in 8 projects that use this

  • obraSkill

    diagnosing-superpowers

    Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.

    Also in 20 projects that use this

  • allanninalSkill

    algorand-vulnerability-scanner

    Scans Algorand smart contracts for 11 common vulnerabilities including rekeying attacks, unchecked transaction fees, missing field validations, and access control issues. Use when auditing Algorand projects (TEAL/PyTeal). (project, gitignored)

    Also in 4 projects that use this

  • allanninalSkill

    cairo-vulnerability-scanner

    Scans Cairo/StarkNet smart contracts for 6 critical vulnerabilities including felt252 arithmetic overflow, L1-L2 messaging issues, address conversion problems, and signature replay. Use when auditing StarkNet projects. (project, gitignored)

    Also in 4 projects that use this

  • farslabSkill

    aws-agentic-ai

    AWS Bedrock AgentCore comprehensive expert for deploying and managing AI agents at scale. Use when working with any AgentCore service including Gateway, Runtime, Memory, Identity, Code Interpreter, Browser, Observability, Agent Registry, or Evaluations. Covers agent deployment, MCP tool integration, credential management, agent discovery, governance workflows, and automated quality assessment. Essential when user mentions AgentCore, agent runtime, agent registry, agent evaluation, MCP gateway, deploy agent, register MCP server, discover agents, evaluate agent quality, agent credentials, or wants to build, deploy, catalog, or monitor AI agents on AWS.

    Also in 3 projects that use this

  • +3 more from Leodorareluctant259
  • +1 more from allanninal

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 178 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this when tasks are coupled or you just want one context.

    line 13
  2. Distinctive:

    Read the plan. Review it critically and note concerns.

    line 19
  3. Distinctive:

    Run the full test suite — green.

    line 36
  4. Distinctive:

    If you're working an issue queue, repeat from the next issue.

    line 54
  5. Distinctive:

    Follow steps exactly; don't skip verifications.

    line 69
  6. Distinctive:

    Never start on main/master without consent.

    line 71

“Common” is measured: kept by at least 6 in 10 of the 178 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Executing Plans

Load the plan, review it critically, run every task, finish with a PR.

Say at the start: "Using the executing-plans skill to implement this plan."

Use this when tasks are coupled or you just want one context. If tasks are independent and subagents are available, subagent-driven-development gives cleaner results (fresh context per task).

1. Load and review

Read the plan. Review it critically and note concerns. If you have concerns, raise them before starting — consult, don't guess. Otherwise create a task list and go. Never start on main/master: cut a feature branch first (or set up a worktree via using-git-worktrees if you want full isolation).

2. Execute

For each task: mark it in progress → follow each step exactly → run the verifications the plan specifies → mark it complete. Work in thin slices — implement, test, verify, commit. If a task feels too big, the incremental-implementation skill covers slicing.

3. Prove it runs

Tests passing isn't the same as working. Before claiming done, prove the change actually runs the way the user would hit it:

  • Run the full test suite — green.
  • Actually run it: start the app / call the endpoint / exercise the CLI. For UI, drive it with agent-browser and confirm the behavior.
  • Paste the real output. Don't claim "it works" without showing it.

4. Finish

This is your normal loop — don't merge or push until the work is done and proven:

git push -u origin <branch>
gh pr create --fill
# review, then:
gh pr merge --squash --delete-branch
git switch main && git pull

Confirm with the user before the merge unless they've said to run it through. If you're working an issue queue, repeat from the next issue.

Stop and ask when

Blocked (missing dep, failing test, unclear step), the plan has a gap, you don't understand a step, or a verification keeps failing. Ask rather than guess. Don't force through a blocker.

Go back to review when

The user updates the plan after your feedback, or the approach needs rethinking.

Remember

  • Review critically first; raise concerns before starting.
  • Follow steps exactly; don't skip verifications.
  • Prove it runs, don't just claim it.
  • Never start on main/master without consent.

Related

  • writing-plans — creates the plan.
  • subagent-driven-development — the fresh-subagent-per-task alternative.
  • using-git-worktrees — full isolation when you want it.
  • incremental-implementation — slice discipline within a task.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.