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.
npx skills add Agent-Clubhouse/Goobers --skill goobers-run-operatorgit clone --depth 1 https://github.com/Agent-Clubhouse/GoobersWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/agent-clubhouse/goobers/goobers-run-operator)<a href="https://agentmods.dev/skills/agent-clubhouse/goobers/goobers-run-operator"><img src="https://agentmods.dev/badge/skills/agent-clubhouse/goobers/goobers-run-operator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/agent-clubhouse/goobers/goobers-run-operator"><img src="https://agentmods.dev/badge/skills/agent-clubhouse/goobers/goobers-run-operator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00039 | $0.02910 |
| Opus 5 | $0.00019 | $0.01455 |
| Sonnet 5 | $0.00008 | $0.00582 |
| Haiku 4.5 | $0.00004 | $0.00291 |
Grade A, and why
goobers-run-operator 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 12d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goobers run operator
Answer operational questions without changing the instance, its repositories,
or provider state. Run goobers-environment-resolver first and use the exact
binary, instance root, config source, and target repository identities it
selects. If any of those remain ambiguous, say what is unresolved instead of
guessing.
Safety boundary
This skill takes no action that changes a run, a work item, a repository, or
configuration. That is a boundary on observable state an operator relies on,
not a claim that every permitted command is free of side effects: trace
opens the telemetry rollup and can create or migrate telemetry.db (see
"Inspect each selected run" below). State that limit plainly if a user asks
whether these commands can alter the instance.
Do not start or stop the daemon, trigger, retry,
resume, rerun, cancel, or abort a run, clear a block, release a claim, repair or
redact a journal, update configuration, modify a repository, or mutate an issue
or pull request. In particular, never invoke goobers run, goobers up,
goobers runs cancel, goobers runs resume, goobers runs rerun,
goobers blocked clear, goobers claims release, goobers journal redact,
provider create/edit/comment/close/merge commands, or a provider request whose
HTTP method is not GET.
Use supported Goobers CLI reads rather than scanning gaggles/*/runs,
events.jsonl, scheduler/, or telemetry.db directly. Do not use daemon log
text as outcome evidence. Do not open transcripts or artifact bodies by
default; use a selected stage transcript only when the user explicitly asks
for transcript-level detail and the structured trace cannot answer the
question. Redact secret-shaped values and summarize rather than dumping raw
content.
Select a bounded evidence set
-
If the user supplied a run ID, select only that run. Otherwise discover the newest runs with:
<goobers> runs list --json --limit=20 <instance-root>Add
--workflow=<name>or--phase=<phase>when the question supplies that scope. The default recent window is 20 runs. State that window in the answer. Expand it with a larger explicit positive limit only when the user requests a wider search or the first window identifies a specific reason to expand. The CLI does not impose a maximum, so keep the selected window as small as the question allows. Never omit--limitand never trace every discovered run.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 247 lines · 39 tokens per session scan A 55a3fb97bfe7
goobers-run-operator is a skill published in the GitHub repository Agent-Clubhouse/Goobers (6 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 2,910 once invoked, about $0.0002 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…