# Pluviobyte/claude-ban-clean

> A macOS-only Claude cleanup skill that audits caches, legacy account fields, login state and device records, backing up and verifying before any narrow-scope removal. It does not lift bans or bypass KYC; it only helps maintain a local install after account restrictions.

- Magnitude: 3.5 out of 10 — Early signal
- Stars: 111 total · +0 stars measured 2026-10-31, 00:27–02:34 UTC, ≈ 19 by evening
- Star trust: star growth looks organic
- Category: Security · Language: Python · Created: 2026-10-29 · Last push: 2026-10-29
- GitHub: https://github.com/Pluviobyte/claude-ban-clean · Page: https://gitnova.dev/en/r/Pluviobyte/claude-ban-clean

## Useful for

- Audit Claude Code caches and telemetry directories read-only before deciding what to remove.
- Back up and verify account token fields, then remove them to force a clean re-login.
- Remove local ant-did and device registry files when explicitly needed, with a timestamped backup batch.

## Why it’s here

- Star-counter measurements on 2026-10-31 (UTC), 00:27–02:34: 111 → 111 stars (+0). This is the change over that interval.
- Estimated end-of-day forecast: about +19 stars, using observed gains and the previous day.
- The repository is 2 days old and already has 111 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #183.
- About 6 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 7
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 43 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0

## Stars per day, last 3 days (oldest → newest, today is partial)

2026-10-29 … 2026-10-31: 87, 24, 0

## Spotted in now

- Top new repositories this week: #183

## More in this category

1. **qybaihe/bla** — 6.9 · Early signal · Security · TypeScript · +37 stars measured 2026-10-31, 00:27–02:33 UTC, ≈ 399 by evening
   BLA (Blind LLM Agents) is a defensive tool that poisons release artifacts (binaries, Electron/ASAR, JS bundles, Python, WASM, models, SQLite) so AI reverse-engineering agents hit resource budgets, follow decoys, and burn tokens while…
   Full card: https://gitnova.dev/en/r/qybaihe/bla.md
2. **N1nEmAn/sapper-v2** — 6.6 · Early signal · Security · Python · +43 stars measured 2026-10-31, 00:27–02:33 UTC, ≈ 208 by evening
   An autonomous multi-agent system for authorized penetration testing: an AI commander dispatches general and soldier agents in parallel, while a layered fact-intent graph preserves knowledge across agent generations.
   Full card: https://gitnova.dev/en/r/N1nEmAn/sapper-v2.md
3. **chris124567/cfsolve** — 6.4 · Early signal · Security · Rust · +63 stars measured 2026-10-31, 00:33–02:33 UTC, ≈ 209 by evening
   Rust library and CLI that solves Cloudflare Turnstile widgets and challenge pages without a headless browser, returning a Turnstile token or cf_clearance cookie by impersonating a browser profile.
   Full card: https://gitnova.dev/en/r/chris124567/cfsolve.md
4. **interplains/Zero-Breach-Toolkit** — 5.3 · Cooling · Security · Python · +12 stars measured 2026-10-31, 00:27–02:33 UTC, ≈ 182 by evening
   Free offline scanner for traces of known mercenary spyware (Pegasus, Predator, Graphite, Candiru) on Windows computers, Android phones and iPhone backups. Read-only, makes no network requests, and states the limits of every check.
   Full card: https://gitnova.dev/en/r/interplains/Zero-Breach-Toolkit.md
5. **MarkBlah/smsofdeath** — 5.2 · Early signal · Security · Java · +5 stars measured 2026-10-31, 00:27–02:33 UTC, ≈ 80 by evening
   Proof-of-concept Android app that sends a crafted 8-byte WAP Push PDU via SMS to crash com.android.phone on the target handset, dropping active calls without user interaction.
   Full card: https://gitnova.dev/en/r/MarkBlah/smsofdeath.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-31 02:43 UTC, updated every 30 minutes.