agentleFS
jimy-rjimy-r/agent-workspace-starter/.claude/skills/wrap/SKILL.md

wrap

Skill1 starsChanged 36 days agoMITView on GitHub

Use when closing out a completed task to integrate it into the required files. Updates the task list, review section, and any registry/index the change belongs in. Invoke via "wrap", "/wrap", "wrap this up", or "close out".

46 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use start, update 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.
  • AnthropicSkill

    start

    Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project.

    Also in 5 projects that use this

  • AnthropicSkill

    update

    Sync tasks and refresh memory from your current activity. Use when pulling new assignments from your project tracker into TASKS.md, triaging stale or overdue tasks, filling memory gaps for unknown people or projects, or running a comprehensive scan to catch todos buried in chat and email.

    Also in 3 projects that use this

  • LangChainSkill

    remember

    Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture learnings.

    Also in 3 projects that use this

  • termdockSkill

    recall

    Retrieves cross-session memories about past decisions, lessons, and patterns. Use when user asks about prior work, past decisions, or mentions a feature. Triggers include check memory, what did we decide, how did we solve.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    build

    Build the TypeSpec Rust emitter from source. Run this after cloning the repo, after pulling changes, or when TypeScript source files have been modified.

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 7 projects that use this

  • +1 more from anthropics

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 40 edited versions we read keep these.

  • 3

    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:

    Stop rediscovering the integration checklist every time a task finishes.

    line 8
  2. Distinctive:

    If the task was not on the notes list, skip this step — don't invent an entry retroactively.

    line 35
  3. Very specific:

    If this task surfaced a mistake pattern worth preventing in future sessions, prepend a ## YYYY-MM-DD — <short title> block to …

    line 50
  4. Distinctive:

    Do not invent history: If a step doesn't apply, say so and skip it.

    line 62
  5. Distinctive:

    Don't overwrite another agent's work: If you see evidence of concurrent edits (unexpected diffs, new files you didn't make), stop and ask …

    line 63

“Common” is measured: kept by at least 6 in 10 of the 40 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

Purpose

Stop rediscovering the integration checklist every time a task finishes. wrap is the canonical close-out ritual: it turns "done in the code" into "done across all the places that need to know about it."

Iron Law

If the task added, renamed, or removed something that lives in a registry, the registry must be updated in the same turn. A shortcut without a row in the Command shortcuts table is invisible next session. No exceptions.

Shape: six linear steps, on purpose

The reference workspace splits this ritual into three phases (the main thread writes a close-out brief, an execution-tier subagent applies it, the main thread reviews the result) because its close-out had grown to about twenty steps run at the session's peak context, where each one re-sends the whole transcript.

This template keeps the linear form deliberately. At six steps the split costs more than it saves: a dispatch adds two main-thread turns of its own, for review and for the report that comes back. Reach for the split when your own close-out has grown past roughly a dozen steps and you can measure what it costs; the reference version is at agent-workspace-architecture.

Procedure

1. Summarize what was done

One or two lines. Name the files touched and the outcome. If nothing material changed, stop here and tell the user — don't fabricate a close-out.

2. Update the active plan — tasks/todo.md

  • Mark plan items complete ([ ] → [x]).
  • Append or fill a ## Review section: what was built, files created/modified, any open follow-ups.

3. Strike through the bullet in tasks/notes.md

Find the matching bullet under the correct ## section. Wrap it in ~~...~~ and append *(Done YYYY-MM-DD — <one-line summary with key file paths>)*.

If the task was not on the notes list, skip this step — don't invent an entry retroactively.

4. Registry / index sweep — THE STEP PEOPLE FORGET

For each row, ask: did this task add, rename, or remove something that belongs here? If yes, update that file in this turn.

Change typeRegistry to update
New / removed verbal shortcutCommand shortcuts table in CLAUDE.md
New protected path.claude/protected-paths.txt
New / removed skill or hookthe "What's inside" table in README.md, if you keep one
Stack / deployment / constraint change on a projectthat project's CONTEXT.md

5. Lessons check

If this task surfaced a mistake pattern worth preventing in future sessions, prepend a ## YYYY-MM-DD — <short title> block to tasks/lessons.md. Skip if nothing was learned — don't pad the file with platitudes.

6. Report

End with a tight summary:

  • Touched: file list with one-line reason each
  • Skipped: registries/files considered and deliberately not updated, with reason
  • Needs user confirmation: anything requiring a user decision before it can be closed

Rules

  • Do not invent history. If a step doesn't apply, say so and skip it.
  • Don't overwrite another agent's work. If you see evidence of concurrent edits (unexpected diffs, new files you didn't make), stop and ask before overwriting.
  • Don't mark tasks complete that aren't verified. wrap assumes the task is already done and verified.
  • Strike-through, don't delete. Historical bullets in tasks/notes.md stay visible with a done date — they're the audit trail.

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.