agentleFS
thoitiettxl-cyberthoitiettxl-cyber/Claw-II/skills/executing-plans/SKILL.md

executing-plans

Skill2 starsChanged 7 months agoMITView on GitHub

Standardize the implementation of an existing implementation plan in OpenClaw-Module Android; Force yourself to stick to scope, follow sequencing/checkpoints, verify in phase, and don't expand the plan without evidence or approval. Use when user already has a written plan and wants execution discipline instead of improvising implementation.

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

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 178 edited versions we read keep these.

  • 8

    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:

    No actual plan exists yet.

    line 52
  2. Distinctive:

    If the supplied plan is incomplete or unsafe, stop and repair the plan before execution.

    line 56
  3. Distinctive:

    If a checkpoint requires approval or evidence before continuing, pause at that boundary.

    line 57
  4. Distinctive:

    Do not silently pull in adjacent work.

    line 67
  5. Distinctive:

    Treat verification as part of the phase, not optional follow-up.

    line 69
  6. Distinctive:

    If reality diverges from the plan, stop and request a plan update instead of improvising.

    line 75
  7. Distinctive:

    Must stay anchored to the provided plan.

    line 97
  8. Distinctive:

    Must not skip verification that the plan depends on.

    line 98

“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

Indexed Reference Map

  • @[SKILL.md#L1-L100] Frontmatter, trigger rules, SOP, output contract.
  • @[references/INDEX.md#L1-L17] Reading order and reference inventory.
  • @[references/execution-loop.md#L1-L14] Phase-by-phase execution loop.
  • @[references/checkpoint-discipline.md#L1-L8] Rules for stop points, approvals, and verification gates.
  • @[references/scope-guard.md#L1-L7] How to avoid improvisational scope drift.
  • @[references/examples.md#L1-L11] Example execution patterns.

Scope

  • In-scope:
    • Executing a pre-existing written plan.
    • Following ordered steps with checkpoints and verification.
    • Reporting progress against the plan rather than freeform implementation logs.
  • Out-of-scope:
    • Writing the initial plan from scratch.
    • Ad-hoc coding with no plan artifact.
    • Final review/merge workflow after execution is complete.

KB Mode Notes

  • Reading order:
    1. references/INDEX.md
    2. references/execution-loop.md
    3. references/checkpoint-discipline.md
    4. references/scope-guard.md
    5. references/examples.md
  • Coverage Matrix:
    • Core execution flow -> execution-loop.md
    • Checkpoints/gates -> checkpoint-discipline.md
    • Scope containment -> scope-guard.md
    • Example patterns -> examples.md
  • Portability note:
    • The skill assumes a plan already exists. If the plan is weak or missing, hand back to planning instead of improvising.

Trigger Rules

  • Positive:
    • User already has a written plan and wants it executed.
    • Prompt contains intent like: execute this plan, follow the plan, do phase 1, continue with the roadmap, implement according to the plan.
    • The main need is disciplined execution with checkpoints, not creating a plan.
  • Negative:
    • No actual plan exists yet.
    • The user is asking for a plan, not execution.
    • The task is mostly debugging or review-handling rather than plan execution.
  • Escalation:
    • If the supplied plan is incomplete or unsafe, stop and repair the plan before execution.
    • If a checkpoint requires approval or evidence before continuing, pause at that boundary.

SOP

  1. Load the plan
    • Identify objective, scope, phases, checkpoints, and verification hooks.
  2. Restate the current phase
    • Execute one bounded phase at a time.
  3. Verify prerequisites
    • Confirm required inputs/state before mutating anything.
  4. Execute only the current scoped step
    • Do not silently pull in adjacent work.
  5. Run the planned verification
    • Treat verification as part of the phase, not optional follow-up.
  6. Record status against the plan
    • Mark done / blocked / partial with reason.
  7. Pause at checkpoints
    • Especially before risky changes, live cutovers, or external actions.
  8. Escalate drift early
    • If reality diverges from the plan, stop and request a plan update instead of improvising.

Error Handling

  • Plan missing critical details:
    • Return to planning and fill the gap before proceeding.
  • Phase blocked by missing dependency/evidence:
    • Mark blocked and state the exact unblocker.
  • New issue appears mid-execution:
    • Contain it to the current phase if possible; otherwise pause and re-plan.
  • User pressures for shortcut past checkpoint:
    • State the risk and required verification/approval.

Output Contract

  • Deliverable:
    • Plan Objective: what is being executed.
    • Current Phase: the bounded step.
    • Execution: actions taken.
    • Verification: proof for the current phase.
    • Status: DONE|PARTIAL|BLOCKED.
    • Next Checkpoint: what gates the next move.
    • Plan Drift: none / observed issue.
  • Validation:
    • Must stay anchored to the provided plan.
    • Must not skip verification that the plan depends on.
  • Compliance Verdict:
    • PASS when execution remains plan-bound and verified; otherwise PARTIAL or FAIL.

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.