agentleFS
Sign inStart free
aaroncohnaaroncohn/openspec-conductor-powerups/skills/status-check/SKILL.md

status-check

Skill1 starsChanged 10 days agoMITView on GitHub

Where things stand, from whichever workspace it's run in. In Babysitter HQ it's a full digest with the workspace table. In an Open Actions, Open Decisions or Open Tests workspace it's how many items are open, each by ID with a line on what it is. In any other workspace it's that workspace's stage, PR and checks, and what's left before merge. Use when the user runs `/babysitter:status-check` or asks "where are we?", "what's open?", "status?".

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. vtmocanu/skills★ 2same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository9 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    Read hq's step 4 ("Re-scan on every wake") and step 6 in <this skill's dir>/../hq/SKILL.md first: in a long run they fade.

    line 18
  2. Distinctive:

    Do the full re-scan from hq's step 4, the same one every wake runs: all open workspaces, read from their newest messages, never a stage …

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

status-check

Say where things stand, in the shape that fits the workspace you're in. Work out which one from this chat first; if it isn't obvious, check in this order:

  1. Babysitter HQ: /babysitter:hq ran in this chat, or .context/babysitter.json exists here.
  2. A queue: this chat's first message is the Open Actions, Open Decisions or Open Tests queue prompt ("You're the Open … queue for /babysitter:hq", or /babysitter in a queue opened before the rename).
  3. Anything else: a change workspace.

Times are in the user's timezone, as in babysitter ("4:10 pm EST"), never UTC.

In Babysitter HQ

Read hq's step 4 ("Re-scan on every wake") and step 6 in <this skill's dir>/../hq/SKILL.md first: in a long run they fade. Then:

  1. Do the full re-scan from hq's step 4, the same one every wake runs: all open workspaces, read from their newest messages, never a stage carried over from the state file.
  2. Take over every workspace on the ADOPT NOW line (from sync-scan locally, watch.py scan in the cloud, or state.py adopt): each one whose user ran /opsx:propose or later that babysitter isn't driving yet, as in hq's step 4. Do it now, before posting, not "once it proposes". Then read and decide each workspace on the CHECK NOW line after it (an offer to start /opsx:propose the user answered, or /opsx:apply named), as in hq's step 4.
  3. Post a digest from python3 <this skill's dir>/../hq/state.py digest, exactly as babysitter's step 6 describes it: what happened (including what you just took over), waiting on you, working on now with estimates, the critical path, the open counts with their IDs, the workspace table, and when the next scheduled digest is due. Don't shorten it because it was asked for: the table is the point. Doesn't reset the digest clock. If state.py paused says it's paused, open with "Paused since <time>." and leave out the next digest's time.

In Open Actions, Open Decisions or Open Tests

From this chat's ledger (every item received, minus every "Done:", "Answered:" or "Result:" line), say how many are open, then list them by ID, one per line, in the order you'd present them (release-blocking, normal, minor; oldest first within each), with a few words on what each one is and the workspace it came from:

4 open decisions.
- OD005 · spam-check threshold (m2.2, apply-m2.2-spam-check) · release-blocking
- OD016 · name of the "replace photo" button (m3.1, apply-m3.1-profile-photo) · minor
…
Say "next" to pick up with OD005, or name an ID to jump to it.

Then stop; don't present an item until the user asks. If the ledger is unclear (a reply never got its "Done:"/"Answered:"/"Result:" line), say which IDs you're unsure about rather than guess.

In any other workspace

One short block on this workspace: its OpenSpec stage (openspec status --change <name>, or "no change" if there isn't one), its branch and whether it's pushed, its PR and the state of its checks (gh pr view --json state,mergeStateStatus,statusCheckRollup), what's left before merge (tasks not done, a review, a rebase), and what it's waiting on, if anything. A table is overkill for one workspace; a few lines will do. If babysitter is driving this workspace ("Via Babysitter:" messages in this chat), say so and point to Babysitter HQ for the whole picture.

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