Skip to content
Back to skills

Status

ASecurity

Print the current autoresearch run's state — goal, baseline, noise floor, best-so-far, run tallies, budget, branch, and the last few iterations. Use for `/ar:status`, "how is the loop doing", "what's the best so far", or any read-only check on an autoresearch experiment. Reconstructs everything from `./.ar/ar.jsonl` on disk, so it works in a fresh session with no prior history. Strictly read-only — never iterates, edits, commits, or reverts.

  • 4 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 24, 2026
ai-agentsgobashgit

Security analysis

A100/100

Scanned October 4, 2026

npx -y skills add emaballarin/ccplugins --skill status --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Status?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Status
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/emaballarin-status/badge)](https://www.skillsdirectory.com/skills/emaballarin-status)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: status
description: Print the current autoresearch run's state — goal, baseline, noise floor, best-so-far, run tallies, budget, branch, and the last few iterations. Use for `/ar:status`, "how is the loop doing", "what's the best so far", or any read-only check on an autoresearch experiment. Reconstructs everything from `./.ar/ar.jsonl` on disk, so it works in a fresh session with no prior history. Strictly read-only — never iterates, edits, commits, or reverts.
allowed-tools: [Read, Glob, Grep, Bash]
---

# /ar:status — read-only state

Report where the run stands. Change nothing.

## Steps

1. Read state:

    ```bash
    cat ./.ar/ar.jsonl 2>/dev/null; git branch --show-current
    ```

    No `ar.jsonl` means no run in this repo — say so, point at `/ar:start`, stop.

2. Reconstruct from the **last** config header and its segment's result lines:
   run count, keep/discard/crash tallies, best-so-far and its commit, plateau
   streak, elapsed budget. Method in
   `${CLAUDE_PLUGIN_ROOT}/references/resume-loop.md` §1.

3. Print the status block:

    ```
    AR ACTIVE — <goal>
      direction   minimize (val_bpb)
      baseline    0.981    noise floor 0.004 (±1.0×)
      best        0.842    @ a1b2c3d  (run 7)
      runs        23 total — 6 keep · 15 discard · 2 crash
      budget      23/100 runs · 4h12m/8h00m
      branch      ar/reduce-val-bpb-22-07-2026  (from main @ 9f31c07)
      last 3      r21 discard 0.851 · r22 discard 0.849 · r23 keep 0.842 ✓
      plateau     0 consecutive non-improvements
    ```

4. Flag anything anomalous without acting on it: the checked-out branch differing
   from `config.branch`, a `Result: pending` trailer on `HEAD` (an iteration
   interrupted mid-measurement), an exhausted budget, or a `stopped` sentinel.

## Hard rules

1. **Read-only.** No edits, commits, branch switches, reverts, or iterations —
   whatever the state looks like. Reporting a problem is the entire job here;
   fixing it belongs to `/ar:resume`.
2. State is read from `./.ar/` only.
3. Report the numbers as recorded. Never recompute a metric, and never infer one
   that was not measured.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.