status

A read-only status report for an autoresearch experiment, where an agent repeatedly tests changes and keeps the ones that improve a result. It reconstructs the run from the repository's saved log.

In plain words
What is it for?
Use it to check how an autoresearch loop is progressing, find its best result and commit, review recent keep or discard decisions, and spot an exhausted budget or stopped run.
Why use it?
It gives a quick view of the experiment's goal, baseline, best result, run counts, budget, branch, and recent attempts without changing anything. It also points out signs that the run may be interrupted or inconsistent.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/emaballarin/ccplugins/status
Any agent
npx skills add emaballarin/ccplugins --skill status
Clone the repo
git clone --depth 1 https://github.com/emaballarin/ccplugins

Made for: Claude Code, Codex.

Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 608 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00115 $0.00608
Opus 5 $0.00057 $0.00304
Sonnet 5 $0.00023 $0.00122
Haiku 4.5 $0.00012 $0.00061

Measured yesterday against content hash 27028ed43479, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

status scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/autoresearch/skills/status/SKILL.md · 52 lines

What it actually says

/ar:status — read-only state

Report where the run stands. Change nothing.

Steps

  1. Read state:

    cat ./.ar/ar.jsonl 2>/dev/null | tail -50; 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.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 52 lines · 115 tokens per session scan A 27028ed43479

Subscribe to this mod's changes

status is a skill published in the GitHub repository emaballarin/ccplugins (3 stars, last pushed 26d ago), licensed MIT. It adds 115 tokens to every session and 608 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens