agentleFS
MorganOnGitHubMorganOnGitHub/tackle/skills/executing-plans/SKILL.md

executing-plans

Skill0 starsChanged 45 days agoMITView on GitHub

Use when carrying out a written plan or task list yourself, in the current session

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

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 178 edited versions we read keep these.

  • 4

    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:

    Substantial: follow the steps below.

    line 13
  2. Distinctive:

    Stop early when reality diverges: If a check fails in a way the plan didn't anticipate, an instruction doesn't fit the code, or the …

    line 21
  3. Distinctive:

    Keep the plan honest: If you deviate for good reason, update the plan and say why.

    line 22
  4. Distinctive:

    Every task's check has run and passed (or its failure has been reported), and deviations from the plan are recorded.

    line 31

“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

Work through a plan task by task, checking each one before moving on and bringing the user in where the plan or reality says they should be.

Scale it

  • Small: work through the task list, verifying as you go.
  • Substantial: follow the steps below.

How

  1. Read the whole plan critically first. Raise gaps, contradictions or risky assumptions before starting, not halfway through.
  2. Track tasks with whatever task tracking the harness provides. If you're on the main branch of a shared repository, check with the user before making substantial changes there, or set up a branch (isolating-workspaces).
  3. For each task: implement it (with testing-first for behavior changes), run its check, and read the result.
  4. Stop at checkpoints the plan marks. Summarize what was done, show the evidence, and ask whether to continue.
  5. Stop early when reality diverges. If a check fails in a way the plan didn't anticipate, an instruction doesn't fit the code, or the approach looks wrong, pause and explain. Don't force the plan through.
  6. Keep the plan honest. If you deviate for good reason, update the plan and say why.

Skip or shorten when

  • The plan has no checkpoints and the tasks are routine. Run straight through and report at the end.
  • The user asks you to go without stopping. Still stop for failures you can't explain.

Done means

Every task's check has run and passed (or its failure has been reported), and deviations from the plan are recorded.

Next

  • verifying-before-claiming before reporting completion
  • requesting-review for substantial or risky changes
  • finishing-work to integrate the result

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.

Reviews can't be read right now.

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.