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 whit3rabbit/clean-room-skill --skill start-overgit 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/start-over)<a href="https://agentmods.dev/skills/whit3rabbit/clean-room-skill/start-over"><img src="https://agentmods.dev/badge/skills/whit3rabbit/clean-room-skill/start-over.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 5.1 | $0.00024 | $0.00855 |
| Opus 5 | $0.00012 | $0.00428 |
| Sonnet 5 | $0.00005 | $0.00171 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
start-over 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 8d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Room Start Over
Start a clean-room run over without overwriting or deleting existing artifacts in place.
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.
Archive First
Require explicit user confirmation before changing artifact locations. Stop if confirmation is absent, authorization is unclear, or the archive target overlaps a source root in a way that would make provenance unclear.
Archive or quarantine previous artifacts before creating new ones:
- Prefer the
task-manifest.jsonartifact_paths.quarantinepath. - Use a user-supplied quarantine path only when it is separated from source roots, contaminated artifact roots, clean roots, and implementation roots.
- Keep contaminated artifacts only under a contaminated-domain archive or quarantine directory.
- Keep clean artifacts only under a clean-domain archive or quarantine directory.
- Do not mix contaminated and clean archives.
- Do not delete artifacts.
- Do not overwrite an existing archive path; create a unique archive directory.
- In the project layout, archive scope is the task folder only. Never archive, move, or quarantine the project root,
clean-room-project.json, or the shared project-levelimplementation/root; sibling tasks depend on them, and implementation content is destination state, not per-task artifact state. - Preserve existing
preflight-goal.json,task-manifest.json, ledgers, handoff packages, behavior specs, skeleton manifests, implementation plans, implementation reports, QC reports, incident records, and open delta tickets.
If safe archive targets cannot be proven from task-manifest.json, root environment, or explicit user input, stop before moving anything.
Restart Gate
Start from the preflight gate, not from prior QC:
- Create a new
preflight-goal.jsonor explicitly reuse a reviewed goal contract before recreating active artifacts. - Reconfirm requester authorization, source or visual evidence scope, allowed actions, prohibited actions, and evidence handling.
- Reconfirm source roots or visual roots, contaminated artifact roots, clean roots, implementation roots, and clean allowed-read roots are separated, and that root path names are not source-derived.
- Preserve source or visual roots and authorization only when they are still valid for the requested restart.
- Create a fresh neutral
task_idby default. Usetask-plus 8 lowercase hex characters unless the user provides an explicitly approved neutral ID. Do not derive the new ID or output directory names from source folder names. - In the project layout, the new task joins the same project by default. Starting a new project instead requires an explicit user choice and a fresh neutral project name (random word pair or
proj-plus 8 lowercase hex, never source-derived). - Record
run_state.generation,run_state.started_at, optionalrun_state.previous_generation_ref, andrun_state.restart_reason. - Recreate
clean-run-context.jsonfrom the new effective preflight and initialization choices; do not carry forward an old clean context by default. - Rebuild
source-index.json, orvisual-index.jsonfor visual fallback runs, unless the user explicitly says the source or visual scope is unchanged and a recorded old index hash can still be validated. - Preserve the selected controller mode only if the user reconfirms it or it is recorded in the still-valid manifest.
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.
- 8d ago First seen · 61 lines · 24 tokens per session scan A dea9a7eb22f3
start-over is a skill published in the GitHub repository whit3rabbit/clean-room-skill (10 stars, last pushed 5d ago), licensed MIT. It adds 24 tokens to every session and 855 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.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…