agentsclimarketplace
Sign in

Plan cleanup

Skill allemaar/open-skills/skills/plan-cleanup

Post-execution cleanup — remove planning artifacts and tech debt left behind after a plan runs. Trigger when the user runs /plan-cleanup, says 'clean up artifacts', 'remove the plan file', or 'no tech debt'. Not /plan-evolve (plans the next version) — plan-cleanup only removes leftovers and adds no new work.From its SKILL.md

Install
npx -y skills add allemaar/open-skills --skill plan-cleanup

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 13 stars13 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.9 KB, 710 tokens by cl100k_base, as published. Nobody here has run it

/plan-cleanup

Remove planning artifacts and tech debt after a plan has been executed. No new work. No scope additions. Just cleanup.

Structured execution spec: protocol.yon. Read it for the canonical rules and step sequence; this file is explanation. The two must stay in sync — if you edit one, update the other and refresh the @STAMP date.

Phase 1 — Identify Artifacts

Scan for artifacts left behind by the planning and execution cycle:

Planning docs (created by /plan-create, /plan-phases, /plan-deep-dive):

  • PLAN.md
  • implementation_plan.md
  • task.md (if created as a plan artifact, not a pre-existing project file)
  • Any *-plan.md files in the project root

Execution scaffolding (created by /plan-execute or setup steps):

  • Temp files, stub files, or files explicitly marked as temporary in the plan
  • Any file whose sole purpose was to scaffold or support the plan run

Tool artifacts:

  • .claude/ directories created incidentally in skill or tool folders (not the user's project .claude/)

For each candidate, verify: is this file needed by the project going forward? If yes, leave it. If it exists only because of the planning cycle, it's an artifact.

Gate: list every artifact found before removing anything. If none found, declare "No artifacts found — workspace is clean" and stop.

Phase 2 — Confirm and Remove

Present the artifact list to the user:

"Found the following planning artifacts:

  • [file 1]
  • [file 2]

Remove all? (y / skip [filename] / cancel)"

On confirmation:

  • Remove each confirmed artifact
  • For git repos: use git rm if the file is tracked, rm if untracked
  • Never remove files outside the current project scope

Gate: do not remove any file not explicitly identified in Phase 1. Do not remove files the user skipped.

Phase 3 — Verify and Commit

  1. Confirm each artifact is gone — list what was removed.
  2. If in a git repo and files were tracked: commit with message chore: remove planning artifacts.
  3. Push if the user's workflow includes pushing (check if prior commits in this session were pushed).

Terminal declaration (required):

  • Cleanup complete — [N] artifacts removed.
  • Cleanup complete — workspace was already clean.
  • Cleanup halted — [reason]. Removed: [list]. Skipped: [list].

Rules

  • MUST list artifacts before removing — never silently delete
  • MUST verify each candidate is a planning artifact, not a project file
  • MUST NOT remove files outside the current project scope
  • MUST NOT remove files the user explicitly skipped
  • MUST end with a terminal declaration

Human output. This skill's handler-facing output obeys the human-output contract (human-output/SKILL.md).

Self-improvement. On completion, run the Self-Improvement Protocol (self-improve/SKILL.md): if this run surfaced a concrete, blocking-or-recurring weakness in this skill, propose a specific fix for the handler to approve. Conservative — silent otherwise. Never auto-apply.

What ships with it: 1 file

4.3 KB alongside SKILL.md

Gives 0 of the 12 instructions most plan spec skills give in 710 tokens

Counted across 1,360 of the 2,617 authors here whose files we hold, read 2026-09-06

  • Ask one question at a timein 73 of 1360
  • Write the spec using the templatein 22 of 1360
  • Ask clarifying questions if neededin 19 of 1360, across 18 files
  • Wait for user confirmation before proceedingin 19 of 1360
  • Save plans to the plans directoryin 17 of 1360, across 13 files
  • Check for product marketing context firstin 16 of 1360, across 5 files
  • Read the plan file completelyin 16 of 1360
  • Order tasks by dependencyin 16 of 1360
  • Gather context from the conversationin 15 of 1360, across 9 files
  • Explore the codebase instead of askingin 15 of 1360, across 13 files
  • Wait for explicit user approvalin 14 of 1360, across 13 files
  • Quiz the user on the breakdownin 13 of 1360, across 7 files

Said here and by no other author read

  • Scan for planning artifacts and execution scaffolding
  • Verify if each candidate file is needed going forward
  • List every artifact found before removing anything
  • Present the artifact list to the user for confirmation
  • Remove each confirmed artifact
  • Commit removed tracked files with a chore message

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.