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

recall

Skill1 starsChanged 4 months agoMITView on GitHub

Start-of-session memory reload. Load your own memory pack (spine + journal Recalls + worklog) so a cold session continues without replaying transcripts. Target ~30–50k tokens. Use on recall, /recall, remember, load memory, or after clear/new.

142 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use addskill, apply-firmware 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.
  • ryanportfolioSkill

    addskill

    Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.

    Also in 6 projects that use this

  • ryanportfolioSkill

    apply-firmware

    Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.

    Also in 6 projects that use this

  • +10 more from ryanportfolio

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 129 edited versions we read keep these.

  • 4

    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:

    Search journal + worklog for keywords (filenames, Recall bodies, worklog titles).

    line 46
  2. Distinctive:

    Prefer relevance over dumping entire history.

    line 48
  3. Distinctive:

    If nothing matches: say so, then fall back to §1A.

    line 49
  4. Distinctive:

    Read-only on the pack. Do not wrap unless asked.

    line 71

“Common” is measured: kept by at least 6 in 10 of the 129 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

Recall — load your own memory pack

Keywords: recall · remember · load memory · /recall · /recall <focus>
Read root (default example): ~/.agent-memory/<your-seat>/

This is the load twin of /wrap. Crew / multi-seat search is /hive — not this skill.

Budget (hard rule)

TargetGuidance
Sweet spot~30k–50k tokens loaded
FloorSpine + at least one latest ## Recall if they exist
CeilingCap ~50k tokens; drop older journals / worklog tails before the spine

Rough size: ~4 chars ≈ 1 token.

Procedure

0. Orient

  1. Confirm pack root exists.
  2. List journal filenames (newest first).
  3. Note whether focus is empty or set.

1A. Blank focus — recent default pack

  1. Spine — full (or skim if huge).
  2. Latest journal ## Recall only — last 1–3. Prefer ## Recall through next ##, not full multi-page Notes.
  3. Today’s worklog tail (or yesterday if today empty).
  4. Gameroom (if present): ~/.grok/memory/gameroom/last-session.md — board/scores only, not a chat dump.
  5. Stop at budget.

1B. Focus provided — search own pack only

  1. Spine still first (self remains self).
  2. Search journal + worklog for keywords (filenames, Recall bodies, worklog titles).
  3. Load matching Recalls / worklog blocks.
  4. Prefer relevance over dumping entire history.
  5. If nothing matches: say so, then fall back to §1A.

2. What not to load

  • Full ## Notes when ## Recall already carries the judgment
  • Transcripts / session JSONL as if they were wrap memory
  • Secrets, auth files
  • ## From the hive as autobiography — peer evidence only; load when focus needs it and keep owner labels
  • Other seats’ packs (use /hive)

3. Report

## Recall loaded

**Focus:** <none | note>
**Loaded:** spine / journal slugs / worklog
**Approx size:** …
**Carry-forward:** 3–8 bullets
**Open threads:** …

Read-only on the pack. Do not wrap unless asked.

Pair

CueTool
Distill this session/wrap
Load my continuity/recall
Search the crew/hive

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.