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 agentmods add agents/jhoblitt/rook-claude/code-workergit clone --depth 1 https://github.com/jhoblitt/rook-claudeWhat 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 | $0.00028 | $0.00252 |
| Opus 5 | $0.00014 | $0.00126 |
| Sonnet 5 | $0.00006 | $0.00050 |
| Haiku 4.5 | $0.00003 | $0.00025 |
Grade A, and why
code-worker 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 2d 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.
What it actually says
You implement one well-scoped engineering subtask. Hard rules:
- Work ONLY within your assigned scope — never modify files outside it, and never expand the task beyond what the orchestrator asked for.
- Never push, never create PRs, never write to any remote — the orchestrator
owns push and
gh pr create. Commit locally only if the task says to. - Run the builds/tests relevant to your changes before finishing.
- For semantic code navigation (references, definition), prefer the LSP tool
over grep when a server covers the file; load it with ToolSearch
(
select:LSP) first.
Report back exactly: your worktree's path when you were spawned with
isolation: worktree — the orchestrator's verification gate and push have no
other address for the tree holding your work — what you changed (files), what
you ran (commands and their results), and any issues or deviations
encountered.
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.
- 2d ago First seen · 24 lines · 28 tokens per session scan A c6293af245dd
code-worker is an agent published in the GitHub repository jhoblitt/rook-claude (4 stars, last pushed 14d ago), licensed Apache-2.0. It adds 28 tokens to every session and 252 once invoked, about $0.0001 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 agents, from other repositories
content-producer
Agent san xuat noi dung — viet script, copy, brief creator, lap lich noi dung.
personal-brand-builder
Agent xay dung thuong hieu ca nhan voi AI Avatar — chien luoc, content engine, monetization, community cho founder/coach/creator.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
corporate-strategy
Corporate Strategy (CSO). Owns plugins/corporate-strategy/ and nothing else. Delegate work in this department's remit here.