agentleFS
Sign inStart free
voardwalker-codevoardwalker-code/wrap-recall-hive/skills/wrap/SKILL.md

wrap

Skill1 starsChanged 4 months agoMITView on GitHub

End-of-session memory ritual. Distill this session into your own memory pack (journal + worklog + relationship spine) so the next session can reload cheaply (~30–50k tokens, not a full transcript). Use on wrap, /wrap, wrap up, goodnight, or before /clear or /new.

45 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use start, update and 9 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

  • 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

  • SentrySkill

    spec

    Produce a verified spec — problem, desired outcome, and acceptance criteria — before building. Use when given a GitHub/Linear issue link, when starting from a fuzzy in-conversation idea, or asked to "figure out what to do" / "scope this" / "what should I build" — whenever the *what* isn't yet pinned down. Grills the ambiguities, checks the premise against the code, and produces acceptance criteria you sign off on — then hands to design-first.

    Also in 3 projects that use this

  • +1 more from anthropics

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 40 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    If peer truth is durable, maintain ## Peer seats (crew) — from this seat’s side only.

    line 99
  2. Distinctive:

    Do not clear the session unless asked.

    line 104

“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

Wrap — end-of-session memory ritual

Keywords: wrap · wrap up · /wrap · goodnight · save the memory
Write root (default example): ~/.agent-memory/<your-seat>/
Configure your real path in the tool skill or environment; never write into another seat’s pack.

This is judgment distillation, not a transcript dump. Do it before clear/new.

Pair: next session loads with /recall. Crew search is /hive (separate tool).

Pack layout

LayerPathRole
Spinerelationship-spine.mdDurable agreements, lore, how the human asks
Journaljournal/<YYYY-MM-DD>-<slug>.mdDistilled ## Recall + notes
Worklogworklog/<YYYY-MM-DD>.mdFacts / paths / status
IndexREADME.mdLoad order + do-nots

Procedure

0. Orient

  1. Skim the spine if it exists.
  2. List recent journal filenames (avoid duplicate slugs).
  3. Today’s date + kebab slug for this task.
  4. Gameroom check: if ~/.grok/memory/gameroom/last-session.md exists and is from this session/day (or the human played the room), fold its board/scores/open threads into journal + worklog. Prefer the room’s Wrap room button for pure play sessions (mechanical, no model $). CLI /wrap still owns full judgment distill when coding + play mixed. Do not dump full table-talk transcripts.

1. Journal (required)

## Recall

<1–3 tight paragraphs for the NEXT cold session.
ONLY what THIS seat and the human did / decided this session.
HARD FENCE: never narrate other agents’ work as "we" or "I".
Peer trails go in ## From the hive only.>

## Notes

### What happened
- …

### Artifacts / paths
- …

### Explicit non-goals / do-nots
- …

### Open threads
- …

## From the hive

<If /hive was used OR peer packs were read: fill the form.
If neither: write exactly _No hive consult this session._>

### Hive consults this session
- **Focus / cue:** …
- **CLI / path:** `python3 path/to/hive.py --focus "…"`
- **Owners hit:** …

### Peer trails (attributed — not me)
- **[owner=… · when=… · kind=…]** <what *they* did> · source: `…`

### What I take from them (my application only)
- … or _none_

### Peer relationship notes (optional)
- … how *this seat's* working relationship with that peer shifted

2. Worklog (required)

### W— — <short title>
**Ask:** …
**Did:**
- … (own actions; peer cites attributed)
**Hive:** none | focus "…" · owners: …
**Status:** Done | Partial | Blocked
**Touched:** paths…
**Not done:** …

3. Spine (only if durable change)

Edit only for lasting agreements, ask-patterns, lore, machine facts, or peer seat relationships.
If peer truth is durable, maintain ## Peer seats (crew) — from this seat’s side only. Do not write into another pack (visa versa = their wrap).

4. Confirm

Report journal path, worklog path, spine updated/unchanged, hive section status.
Do not clear the session unless asked.

Anti-patterns

  • Transcript dump
  • Folding hive/peer work into ## Recall as autobiography
  • Omitting ## From the hive after a hive session
  • Cross-writing another seat’s pack
  • Secrets / API keys / auth files in any layer

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.

Check your setup, free