agentleFS
huntiehuntie/skills/recall/SKILL.md

recall

Skill0 starsChanged 21 days agoMITView on GitHub

Rebuild where a topic stands from the vault, the checkouts, and GitHub, and hand back a short current-state brief before work starts or resumes. Use when the user invokes /recall or says "catch me up", "where did I leave off", or "what's the state of X".

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

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

  • 0

    Common

    Most of the 129 edited versions we read keep these.

  • 2

    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. Distinctive:

    Read-only. The deliverable is a brief, not a change, and the reading stays on the named topic and window.

    line 12
  2. Distinctive:

    Write the brief to the contract below, in plain prose, citing a plan path, a branch, or a PR number for each claim.

    line 18
  3. Very specific:

    If a plan's status tag disagrees with live state, end with the one-line correction and offer to update it per vault/COMMITTING_POLICY.md.

    line 27

“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

Read-only. The deliverable is a brief, not a change, and the reading stays on the named topic and window. Heavy reads go to subagents where available; the main thread keeps findings and the brief.

  1. Lock the scope before reading: the topic, the window ("recent" means the last seven days unless the user says otherwise), and which checkouts under projects/ it touches. State the scope back in one line. If the user already gave a full state capsule, use it and skip the mining.
  2. Read the vault for the topic: vault/index.md; every plan whose overview mentions it, with its status tag and Branch: line; the overlay under vault/memory/<repo>/ for each checkout in scope; and the decisions log where the topic is devroot itself. A status tag is a claim to verify, not the answer.
  3. Read live state in each checkout in scope: the current branch, the branches the plans name plus any whose names match the topic, commits in the window on them, WIP parking commits and stashes, and the working tree. In a Sapling checkout (devroot.vcs=sapling), also the draft stacks, sl log -r 'draft()' from inside the checkout, since a detached stack is on no branch. Then gh pr list --author @me and gh pr view for any PR those branches or plans name, with review and check state.
  4. Reconcile. A plan or note is history; git and GitHub are current truth. Where they disagree, the brief says so and names the stale one. Chat history is not a source unless the user asks for it, and then only this workspace's own sessions.
  5. Write the brief to the contract below, in plain prose, citing a plan path, a branch, or a PR number for each claim. Adjacent topics stay out unless they block this one. When it outgrows a screen, cut detail before cutting threads.

Contract:

  • Capsule. At most five bullets: what the work is and where it stands overall.
  • Threads. One line each, opening with exactly one tag: [merged #N], [open PR #N], [in flight <branch>], [verified, uncommitted], [planned, not started], or [shelved]. Every thread gets a tag; an untagged thread is not done being investigated.
  • Problems. At most five, the recurring ones, including anything tried and reverted so the next attempt starts where the last one failed.
  • Next move. The single most useful concrete action.

If a plan's status tag disagrees with live state, end with the one-line correction and offer to update it per vault/COMMITTING_POLICY.md; do not update it unasked. When the next move is resuming a plan, name its branch and the scripts/checkout <owner/repo>@<branch> that lands on it.

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.