agentleFS
serbanghitaserbanghita/plan-critique-skills/skills/archive/SKILL.md

archive

Skill13 starsChanged 2 months agoMITView on GitHub

Archive a completed or abandoned plan for future reference

22 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use distill, plan and 3 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.
  • HK-hubSkill

    distill

    Strip designs to their essence by removing unnecessary complexity. Great design is simple, powerful, and clean. Use when the user asks to simplify, declutter, reduce noise, remove elements, or make a UI cleaner and more focused.

    Also in 3 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 5 projects that use this

  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    test

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

18 rules. 0 are common, 5 are distinctive, and 13 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 13

    Very specific

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

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

    Read .claude/plan-critique-config.json and get plansFolder path from settings.

    line 13
  2. Very specific:

    If the file doesn't exist or plansFolder is not set or is an empty string: Respond with "No plans folder configured.

    line 14
  3. Very specific:

    Read the current session's plan from [plansFolder]/.sessions/[sessionPID] if it exists.

    line 20
  4. Distinctive:

    If no plan folders exist: Respond with "No plans found.

    line 23
  5. Very specific:

    If sessionPlan exists and matches a plan folder, auto-select it.

    line 25
  6. Very specific:

    Check prerequisites. If [plansFolder]/[selected-plan]/plan.md does not exist or is empty: Respond with "Nothing to archive.

    line 38
  7. Very specific:

    Ensure [plansFolder]/archived/ exists, create it if not.

    line 40
  8. Very specific:

    Read plan.md to get the plan title (first H1 heading).

    line 42
  9. Very specific:

    Read critique.md to get keywords (if available)

    line 43
  10. Very specific:

    Read execution-log.md to get execution status (if available)

    line 44
  11. Very specific:

    Create the archive folder at [plansFolder]/archived/[folder-name]/

    line 47
  12. Very specific:

    Create archive-info.md in the archive folder using the format in archive-info-format.md.

    line 51
  13. Very specific:

    Delete the original plan folder [plansFolder]/[selected-plan]/ entirely.

    line 53
  14. Very specific:

    Delete [plansFolder]/.sessions/[sessionPID] if it contains the archived plan slug.

    line 55
  15. Distinctive:

    Never include critique.md in the archive (only keywords are preserved in archive-info.md)

    line 67
  16. Distinctive:

    Always include the full original plan and all supporting files

    line 68
  17. Distinctive:

    Use current timestamp for the archive folder name

    line 70
  18. Distinctive:

    Always delete the original plan folder after archiving

    line 72

“Common” is measured: kept by at least 6 in 10 of the 18 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

You are archiving the user's completed (or abandoned) plan for future reference.

To do this, follow these steps precisely:

  1. Read .claude/plan-critique-config.json and get plansFolder path from settings. If the file doesn't exist or plansFolder is not set or is an empty string: Respond with "No plans folder configured. Run /plan:create first to set up."
  2. Get the Claude Code process ID by running: echo $PPID. Store this as sessionPID.
  3. Clean up stale sessions: Scan [plansFolder]/.sessions/ for files. For each file named with a PID, check if that process is still running via kill -0 [PID] 2>/dev/null. If the command fails (process not running), delete that session file. This is non-blocking cleanup.
  4. Read the current session's plan from [plansFolder]/.sessions/[sessionPID] if it exists. Store as sessionPlan.
  5. Scan [plansFolder]/ for subdirectories (each subdirectory is a plan). Exclude archived/ and .sessions/ folders and any files, only list plan directories. If no plan folders exist: Respond with "No plans found. Nothing to archive."
  6. Select the plan to archive:
    • If sessionPlan exists and matches a plan folder, auto-select it. Inform the user: "Using current session plan: [sessionPlan]"
    • Else if only one plan exists, auto-select it and inform user.
    • Otherwise, ask the user to select a plan from the list. Example:
      Available plans:
      1. add-user-authentication
      2. refactor-database-layer
      3. implement-caching
      
      Which plan would you like to archive? [1-3]
  7. Check prerequisites. If [plansFolder]/[selected-plan]/plan.md does not exist or is empty: Respond with "Nothing to archive. Plan file is missing or empty."
  8. Ensure [plansFolder]/archived/ exists, create it if not.
  9. Extract metadata:
    • Read plan.md to get the plan title (first H1 heading). If no title, use folder name.
    • Read critique.md to get keywords (if available)
    • Read execution-log.md to get execution status (if available)
  10. Generate archive folder name using format: YYYY-MM-DD_HH-MM-SS_[slug]/ Example: 2026-01-12_14-30-00_add-user-authentication/
  11. Create the archive folder at [plansFolder]/archived/[folder-name]/
  12. Copy contents from [plansFolder]/[selected-plan]/ to the archive:
    • Include: plan.md, execution-log.md (if exists), all other files (SQL, images, etc.)
    • Exclude: critique.md, execution-state.json
  13. Create archive-info.md in the archive folder using the format in archive-info-format.md.
  14. Delete the original plan folder [plansFolder]/[selected-plan]/ entirely.
  15. Clean up session references to the archived plan:
    • Delete [plansFolder]/.sessions/[sessionPID] if it contains the archived plan slug.
    • Scan all other session files and delete any that reference the archived plan (handles stale references).
  16. Respond with confirmation:
    Plan archived to: [plansFolder]/archived/[folder-name]/
    
    The original plan folder has been removed.
    Create a new plan with `/plan:create`.

Notes:

  • Never include critique.md in the archive (only keywords are preserved in archive-info.md)
  • Always include the full original plan and all supporting files
  • Include execution log only if the plan was executed
  • Use current timestamp for the archive folder name
  • Preserve the original file structure within the archived folder
  • Always delete the original plan folder after archiving
  • It is valid to archive a plan that was never executed (abandoned, reference, or superseded plans). In this case, the execution status will be NOT_EXECUTED.

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.