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 skills/whit3rabbit/clean-room-skill/refocusnpx skills add whit3rabbit/clean-room-skill --skill refocusgit clone --depth 1 https://github.com/whit3rabbit/clean-room-skillWrote 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/whit3rabbit/clean-room-skill/refocus)<a href="https://agentmods.dev/skills/whit3rabbit/clean-room-skill/refocus"><img src="https://agentmods.dev/badge/skills/whit3rabbit/clean-room-skill/refocus.svg" alt="Measured on agentmods" 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 | $0.00023 | $0.01076 |
| Opus 5 | $0.00012 | $0.00538 |
| Sonnet 5 | $0.00005 | $0.00215 |
| Haiku 4.5 | $0.00002 | $0.00108 |
Grade A, and why
refocus 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 4d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Room Refocus
Refocus realigns the current run to the declared scope, controller policy, artifact schemas, and clean-room boundary.
Refocus does not optimize, expand, or reinterpret the task. It does not invent new requirements or add behavior beyond preflight-goal.json, task-manifest.json, clean-run-context.json, ledgers, implementation plan/report, QC, and abstract delta tickets.
Use the canonical clean-room skill workflow and references in this plugin. Preserve the same clean-room boundary, role separation, artifact schemas, leakage rules, implementation-root rules, and hook expectations.
Audit
Compare current artifacts to the canonical gate checklist:
- Scope gate recorded authorization, roots, boundaries, prohibited actions, evidence handling, selected target profile, Agent 0-4 pipeline, and Agent 1.5 sanitizer role for new runs.
- Preflight goal exists for new runs, validates against
preflight-goal.schema.json, and is referenced bytask-manifest.jsonwithpreflight_goal_refandpreflight_goal_sha256. - Task manifest records the required
handoff_sequenceand does not skip Stage 0. - Initialization snapshot exists when init preferences were used, and reusable
init-config.jsondrift is reported instead of silently applied. clean-run-context.jsonexists before clean roles run and excludes source roots, visual roots, contaminated roots, source index refs, visual index refs, and ledger paths.clean-run-context.jsonrecords artifact-only coordination: Agent 0 does not directly steer Agent 2, Agent 3, or Agent 4, and clean implementation/polish roles report to Agent 0 only at terminal status.- When context management is enabled, the next role launch can be driven by a fresh
role-session-brief.jsoninside the recorded budgets.controller-status.jsonremains contaminated-side only. - Implementation roots are recorded, separated, and not source-derived.
- Source index or visual-index fallback preflight exists when required and remains contaminated-only.
- Decomposition produced neutral
task-manifest.jsonunits. - Contaminated analysis wrote draft behavior specs without implementation code.
- Agent 1.5 sanitization ran before handoff, or older artifacts clearly predate the Agent 1.5 gate and require review before reuse.
- Handoff package excludes full
task-manifest.json,source-index.json,visual-index.json, raw screenshots, source or visual paths, raw diffs, copied comments, copied visible words, private identifiers, exact UI palettes/layouts/iconography, source-shaped pseudocode, and contaminated ledgers. - Agent 2 produced clean-only
implementation-plan.jsonwhen the run reached that gate. - Agent 3 produced
implementation-report.jsonwhen the run reached implementation. - Non-terminal Agent 3 implementation reports were not used as Agent 0 feedback or guidance.
- QC produced
qc-report.jsonwith schema, leakage, coverage, and abstract delta ticket status when the run reached that gate. - Agent 4 produced
polish-report.jsonwhen the run reached final polish review. - Contaminated verification returned only abstract delta tickets.
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.
- 4d ago First seen · 72 lines · 23 tokens per session scan A 900578eb74d5
refocus is a skill published in the GitHub repository whit3rabbit/clean-room-skill (10 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 1,076 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…