refocus

refocus is a skill for Claude Code, Codex from whit3rabbit/clean-room-skill. It costs 23 tokens per session (1,076 once invoked), scanned A, original, MIT.

Herramienta que revisa una ejecución existente de Clean Room, un proceso con límites y comprobaciones definidos, y la orienta hacia los controles que faltan.

In plain words
What is it for?
Sirve para comprobar autorizaciones, límites, archivos de preparación, secuencia de tareas, controles de limpieza y otros documentos de una ejecución de Clean Room.
Why use it?
Ayuda a encontrar pasos omitidos, documentos ausentes o incumplimientos del alcance declarado sin cambiar los objetivos ni ampliar el trabajo.

Skill for Claude CodeCodex

Part of the clean-room plugin — 10 skills, 7 agents shipped together

Install

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.

agentmods
npx agentmods add skills/whit3rabbit/clean-room-skill/refocus
Any agent
npx skills add whit3rabbit/clean-room-skill --skill refocus
Clone the repo
git clone --depth 1 https://github.com/whit3rabbit/clean-room-skill

Made for: Claude Code, Codex.

Or install clean-room, the plugin that ships this one along with the rest of its 10 skills, 7 agents.

Wrote 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.

agentmods badge for refocus

README.md
[![agentmods](https://agentmods.dev/badge/skills/whit3rabbit/clean-room-skill/refocus.svg)](https://agentmods.dev/skills/whit3rabbit/clean-room-skill/refocus)
Your own site
<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>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,076 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 4d ago against content hash 900578eb74d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

skills/refocus/SKILL.md · 72 lines

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 by task-manifest.json with preflight_goal_ref and preflight_goal_sha256.
  • Task manifest records the required handoff_sequence and does not skip Stage 0.
  • Initialization snapshot exists when init preferences were used, and reusable init-config.json drift is reported instead of silently applied.
  • clean-run-context.json exists before clean roles run and excludes source roots, visual roots, contaminated roots, source index refs, visual index refs, and ledger paths.
  • clean-run-context.json records 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.json inside the recorded budgets. controller-status.json remains 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.json units.
  • 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.json when the run reached that gate.
  • Agent 3 produced implementation-report.json when the run reached implementation.
  • Non-terminal Agent 3 implementation reports were not used as Agent 0 feedback or guidance.
  • QC produced qc-report.json with schema, leakage, coverage, and abstract delta ticket status when the run reached that gate.
  • Agent 4 produced polish-report.json when the run reached final polish review.
  • Contaminated verification returned only abstract delta tickets.

Read the full file on GitHub · 72 lines

Changes

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.

  1. 4d ago First seen · 72 lines · 23 tokens per session scan A 900578eb74d5

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

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.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens