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 vosslab/vosslab-skills --skill stay-busygit clone --depth 1 https://github.com/vosslab/vosslab-skillsWrote 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/vosslab/vosslab-skills/stay-busy)<a href="https://agentmods.dev/skills/vosslab/vosslab-skills/stay-busy"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/stay-busy/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/vosslab/vosslab-skills/stay-busy"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/stay-busy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00050 | $0.02563 |
| Opus 5 | $0.00025 | $0.01282 |
| Sonnet 5 | $0.00010 | $0.00513 |
| Haiku 4.5 | $0.00005 | $0.00256 |
Grade A, and why
stay-busy 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 11d 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stay busy
Big picture
One-line principle: when stuck, find a solution. When the manager has no obvious next plan task, the answer is more dispatched work, not idle.
Finish the obvious comes first. This skill is layered on top of the
"Finish the obvious" core philosophy in docs/REPO_STYLE.md. If a plan
task, in-flight workstream, or open verification step still has obvious
next actions, the manager takes those FIRST. stay-busy fires only after
the obvious queue is empty. See ## Finish before expanding for the gate
that enforces this, and Workflow step 2 for where the gate runs.
The failure this skill prevents: the manager spends a few minutes making a plan, then sits idle for hours or days. A short task gets finished and the manager stops, even though the user wanted continued exploration.
This skill exists to inflate scope by roughly two orders of magnitude when the user is away from the keyboard, overnight or across several days. They are going to bed, stepping out, or running a session unattended, and they want to wake up to finished artifacts, not a queue of pending questions to answer.
Success = completed work the user can read on returning. Failure = a stack of "should I do X?" prompts, or a milestone declared done while obvious follow-on testing was skipped.
Four anchor activities, named by the user, define the work stay-busy generates:
- Write up results. Synthesize completed runs into reports that compare, summarize, or rank. Long-form (25-100 page) reports are a valid single workstream when enough evidence has accumulated to synthesize.
- A/B (or A/B/C/D) testing. Run methodologies, configurations, or alternative implementations side by side and report the comparison.
- Side-quest experiments. Launch subagents to explore tangents that may
inform future work, labeled
SIDE QUEST. - Audit the codebase. Read-only correctness, style, contract, and coverage sweeps producing inspectable artifacts.
Default workstream shape in away-mode is expansive, not small. "Small, concrete recovery task" is wrong when the user is asleep. The right shape is a test suite spanning N methodologies, a stress matrix across M configurations, an audit covering K subsystems, a screenshot gallery across V viewports.
What ships with it
27 files 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.
- agents/openai.yaml 204 B
- references/big_picture.md 11 KB
- references/boundaries.md 3.2 KB
- references/ideas_checklist.md 2.8 KB
- references/operating_modes.md 2.9 KB
- references/scaling_and_cleanup.md 2.2 KB
- references/workstream_templates.md 6.2 KB
- references/workstreams/alternative_prototype.md 767 B
- references/workstreams/audit.md 757 B
- references/workstreams/benchmark_and_profiling.md 708 B
- references/workstreams/cleanup.md 767 B
- references/workstreams/coverage_gap.md 1.3 KB
- references/workstreams/data_quality.md 1.2 KB
- references/workstreams/dead_code.md 1.3 KB
- references/workstreams/documentation_example_refresh.md 1.3 KB
- references/workstreams/failure_investigation.md 694 B
- references/workstreams/implementation.md 769 B
- references/workstreams/next_iteration_push.md 909 B
- references/workstreams/performance_regression.md 1.3 KB
- references/workstreams/regression_and_bisect.md 632 B
- references/workstreams/release_notes_summary.md 1.8 KB
- references/workstreams/release_readiness.md 1.5 KB
- references/workstreams/report.md 2.5 KB
- references/workstreams/screenshot_and_evidence.md 662 B
- references/workstreams/spec_conformance.md 1.2 KB
- references/workstreams/stress_and_clutter.md 740 B
- references/workstreams/test.md 791 B
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.
- 11d ago First seen · 282 lines · 50 tokens per session scan A aad6905bfd54
stay-busy is a skill published in the GitHub repository vosslab/vosslab-skills (2 stars, last pushed 15d ago), licensed MIT. It adds 50 tokens to every session and 2,563 once invoked, about $0.0003 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.