start-over

start-over is a skill for Claude Code from whit3rabbit/clean-room-skill. It costs 24 tokens per session (855 once invoked), scanned A, original, MIT.

A clean-room workflow action that preserves the current task's artifacts and starts a new run from the initial scope check. Clean-room work separates source review from implementation to limit information leakage.

In plain words
What is it for?
Use it when a clean-room task must be restarted, with old contaminated and clean artifacts moved into separate archives or quarantine folders after confirmation.
Why use it?
It provides a fresh start without deleting or overwriting the previous run's files.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

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

Good fit Use it when a clean-room task must be restarted, with old contaminated and clean artifacts moved into separate archives or quarantine folders after confirmation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/whit3rabbit/clean-room-skill/start-over
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.

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

Made for: Claude Code.

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 start-over

README.md
[![agentmods](https://agentmods.dev/badge/skills/whit3rabbit/clean-room-skill/start-over.svg)](https://agentmods.dev/skills/whit3rabbit/clean-room-skill/start-over)
Your own site
<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>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 855 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00024 $0.00855
Opus 5 $0.00012 $0.00428
Sonnet 5 $0.00005 $0.00171
Haiku 4.5 $0.00002 $0.00085

Measured 8d ago against content hash dea9a7eb22f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

skills/start-over/SKILL.md · 61 lines

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.json artifact_paths.quarantine path.
  • 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-level implementation/ 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.json or 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_id by default. Use task- 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, optional run_state.previous_generation_ref, and run_state.restart_reason.
  • Recreate clean-run-context.json from the new effective preflight and initialization choices; do not carry forward an old clean context by default.
  • Rebuild source-index.json, or visual-index.json for 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.

Read the full file on GitHub · 61 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. 8d ago First seen · 61 lines · 24 tokens per session scan A dea9a7eb22f3

Subscribe to this mod's changes

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.

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

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

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…

microsoft/vscode · 72 tokens