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 jared833/claude-code-hooks --skill busy-workgit clone --depth 1 https://github.com/jared833/claude-code-hooksWrote 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/jared833/claude-code-hooks/busy-work)<a href="https://agentmods.dev/skills/jared833/claude-code-hooks/busy-work"><img src="https://agentmods.dev/badge/skills/jared833/claude-code-hooks/busy-work/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/jared833/claude-code-hooks/busy-work"><img src="https://agentmods.dev/badge/skills/jared833/claude-code-hooks/busy-work.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 | $0.00054 | $0.01395 |
| Opus 5.5 | $0.00022 | $0.00558 |
| Sonnet 5.5 | $0.00011 | $0.00279 |
| Haiku 4.5 | $0.00005 | $0.00139 |
Grade A, and why
busy-work 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 2mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Busy Work
Run an autonomous work session against the shared backlog, which lives in the Notion
Backlog database under the Ops Command Center page (data source
collection://YOUR-BACKLOG-DATA-SOURCE-ID). You (the main session) are the
orchestrator, do not spawn a separate orchestrator agent.
Repointed 2026-07-19. This skill used to read aide-data/memory/backlog.md and promote
leftovers into todo.md. Both files were demoted to pointers on 2026-07-12 when Notion
became the source of truth for state, so a run against them would have found nothing to do.
What counts as zero-involvement
Only work items that need nothing from Jared:
- Fair game: research and discovery write-ups, recommendations, plans, local code
changes in
<HOME>\projects\*, doc edits, reading screenshots referenced in backlog items and writing assessments. - Off limits: anything in the "Personal Items" section; anything requiring Jared's
decision, his accounts/credentials, spending money, sending outward communication
(emails, texts, posts), or destructive operations. For these, write a short note in
the session log, create a row in the Notion Tasks database (data source
collection://YOUR-TASKS-DATA-SOURCE-ID) so it does not get lost, and move on. If the body names steps to take, write them as a bulleted or numbered list, one action per bullet, in order; keep context and dependencies as prose.
Procedure
-
Read the Notion Backlog DB and pick the zero-involvement work items. Read the Notion Tasks DB in the same pass so you do not start something already open or already Done.
A SQL query returns properties only. It never returns the page body. Jared writes the scope of an item in the body, under a link, so a row whose title and Notes look empty or vague is usually fully specified one
notion-fetchaway. On 2026-07-28 a triage pass called the Instagram and YouTube rebrand rows too vague to act on, and on 2026-07-29 this skill repeated it, both times off the title and Notes alone. The body of each said which account and what was wrong with it. Before you skip ANY row as vague, unclear or underspecified,notion-fetchthat page and read its body. Skipping on a title is the one move this procedure has actually got wrong twice.
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.
- 2mo ago First seen · 88 lines · 54 tokens per session scan A 9d1cfa49fcc5
busy-work is a skill published in the GitHub repository jared833/claude-code-hooks (2 stars, last pushed 4d ago), licensed MIT. It adds 54 tokens to every session and 1,395 once invoked, about $0.0002 per session on Opus 5.5. 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
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…