agentleFS
andreymudriandreymudri/claude-teammates/skills/executing-plans/SKILL.md

executing-plans

Skill3 starsChanged 10 days agoMITView on GitHub

Use when you have a written implementation plan to execute inline in this session, with checkpoints - the non-fleet execution path.

189 other projects use a version of this, 1 of them edited.

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, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 177 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the work turns out to be bigger than expected mid-run, hand it to parallel-execution without translating anything — the state is already …

    line 24
  2. Distinctive:

    Never start implementation on main/master without explicit consent from your human partner.

    line 27
  3. Distinctive:

    Read it fully before touching code.

    line 31
  4. Very specific:

    After all tasks are complete and verified, use finishing-a-development-branch (if available) or otherwise confirm tests pass and present …

    line 55
  5. Distinctive:

    Stop immediately when you hit a blocker (missing dependency, failing test, unclear instruction), when the plan has a gap that prevents …

    line 60
  6. Distinctive:

    No gate manifest required.

    line 69

“Common” is measured: kept by at least 6 in 10 of the 177 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

Adapted from the MIT-licensed superpowers plugin by Jesse Vincent. See NOTICE.md.

Execute a written plan inline, in this session, task by task, checkpointing with your human partner as you go. This is the counterpart to parallel-execution: same run state, different cadence. Use using-fleetmates to decide which one applies before reaching for this skill.

1. Initialize the run

node "<fleetmates root>/scripts/cli.mjs" init-run <planPath> --run <runId> --root <project root>

This writes .fleetmates/<runId>/plan.json and status.json — the same shared state a fleet run would write. Because of that:

  • node "<fleetmates root>/scripts/cli.mjs" digest --run <runId> --root <project root> renders this run unchanged, whether it ran inline or across teammates.
  • fleet-lifecycle resume <runId> can resume it later.
  • If the work turns out to be bigger than expected mid-run, hand it to parallel-execution without translating anything — the state is already in the shape it expects.

Never start implementation on main/master without explicit consent from your human partner.

2. Review the plan critically

Read it fully before touching code. Raise concerns with your human partner before starting — gaps, unclear steps, or a task that looks bigger than a single sitting.

3. Execute and checkpoint

Work through tasks in dependency order. Follow each step; run the verifications it specifies.

Checkpoint with your human partner per task, or per small batch of related tasks — not automatically per phase the way a fleet gate does, and not silently at the end of the whole plan. Report what changed, what you verified, and any deviation from the plan before moving on.

Gate manifest is optional here

A fleet phase demands a fleetmates.gate.json manifest before it will pass. Inline work does not need one. When no manifest exists, checkpoint against the plan's own verification steps instead of demanding one be written first.

Do not require a phase structure, a manifest, or a reviewer dispatch for small inline work. Ceremony that makes a two-task change expensive is ceremony that gets skipped — and a skipped skill protects nothing. Reserve that machinery for work that has actually grown into a fleet (see parallel-execution and phase-gate).

4. Finish

After all tasks are complete and verified, use finishing-a-development-branch (if available) or otherwise confirm tests pass and present integration options to your human partner.

When to stop and ask for help

Stop immediately when you hit a blocker (missing dependency, failing test, unclear instruction), when the plan has a gap that prevents starting, or when a verification fails repeatedly. Ask rather than guess.

Remember

  • Shared state with the fleet path: .fleetmates/<run-id>/, init-run, digest, resumable via fleet-lifecycle.
  • Checkpoint per task or per batch, with the user — not per phase, not automated.
  • No gate manifest required; the plan's own verification steps stand in for one.
  • Scale up to parallel-execution any time without rewriting state.

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.