clean-install-reset

A checklist for returning a computer's noisy-coding installation setup to a clean starting state. It audits configuration files, hooks, plugin records, marketplace entries, and an optional Docker volume before changes are made.

In plain words
What is it for?
Use it when testing a clean installation, resetting noisy-coding or legacy grok-voice setup, or investigating stale hooks, plugins, MCP entries, and Docker data.
Why use it?
Old installation leftovers can make a fresh test behave differently from a new user's setup. The checklist helps find those leftovers and keeps backups of edited files.

Skill for Claude CodeCodex

Part of the noisy-coding plugin — 7 skills, 2 commands, 4 hooks, 1 MCP server 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/noisy/noisy-coding/clean-install-reset
Any agent
npx skills add noisy/noisy-coding --skill clean-install-reset
Clone the repo
git clone --depth 1 https://github.com/noisy/noisy-coding

Made for: Claude Code, Codex.

Or install noisy-coding, the plugin that ships this one along with the rest of its 7 skills, 2 commands, 4 hooks, 1 MCP server.

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 955 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00089 $0.00955
Opus 5 $0.00044 $0.00477
Sonnet 5 $0.00018 $0.00191
Haiku 4.5 $0.00009 $0.00096

Measured 3d ago against content hash 93bb287af564, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

clean-install-reset scanned grade B with 1 finding 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 3d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

settings afterwards (`grep -i noisy ~/.claude/settings.json`).
.claude/skills/clean-install-reset/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clean-slate reset for install testing

Purpose: bring the machine to the state of a NEW user, so the plugin install path (marketplace addplugin install/noisy-coding:setup) can be tested honestly. This skill is a checklist and a conversation script, not a delete script — AUDIT first, show the user a table of findings, ASK about the destructive choices, and back up whatever you edit (one local directory, e.g. .cleanup-backup-<date>/, kept out of git).

Expect the permission classifier to block some steps (editing settings files from scripts, docker rm): fall back to the Edit tool for files, and hand the user a ready !-prefixed command for the docker parts.

Where artifacts hide (audit ALL of these)

  1. ~/.claude/settings.json — installer-era hooks (docker exec -i noisy-coding …) and enabledPlugins / extraKnownMarketplaces entries.
  2. ~/.claude.json — a user-scope mcpServers.noisy-coding entry (from the manual claude mcp add path) and dead projects entries (e.g. the old grok-voice-mcp checkout).
  3. ~/.claude/plugins/installed_plugins.json, known_marketplaces.json (marketplace noisy), cache/noisy/. Prefer claude plugin uninstall / claude plugin marketplace remove over hand-editing when available.
  4. Plugin hooks live inside the plugin cache — they vanish with the plugin; no separate cleanup, but VERIFY nothing noisy-related remains in the main settings afterwards (grep -i noisy ~/.claude/settings.json).
  5. ~/.claude/skills/ — hand-copied grok-voice* relics.
  6. ~/.config/noisy-coding/ — stale rewake-*.lock files and sessions.json are always safe to delete; credentials.json, history.json, character.json, settings.json are USER DATA — ask (see below).
  7. ~/.config/grok-voice/ — pre-rename leftovers, safe to delete.
  8. Docker: container noisy-coding, volume noisy-coding-config, legacy images (grok-voice*, old noisy/noisy-coding). docker rm needs the user; give the exact command.
  9. Secondary Claude profiles the user may have (e.g. ~/.claude-personal) — same checks as 1–3. Ask which profiles are in scope.

Read the full file on GitHub · 63 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. 3d ago First seen · 63 lines · 0 tokens per session scan B 93bb287af564

Subscribe to this mod's changes

clean-install-reset is a skill published in the GitHub repository noisy/noisy-coding (6 stars, last pushed 4d ago), licensed MIT. It adds 89 tokens to every session and 955 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.