Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add cwf818/topgauge/plugin install creditgaugeWrote 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/commands/cwf818/topgauge/clean)<a href="https://agentmods.dev/commands/cwf818/topgauge/clean"><img src="https://agentmods.dev/badge/commands/cwf818/topgauge/clean/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/cwf818/topgauge/clean"><img src="https://agentmods.dev/badge/commands/cwf818/topgauge/clean.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00017 | $0.00616 |
| Opus 5.5 | $0.00007 | $0.00246 |
| Sonnet 5.5 | $0.00003 | $0.00123 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
clean 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 1mo 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.
creditgauge :clean
Targets the .bak.YYYYMMDDTHHMMSS files our install/uninstall scripts
leave behind:
settings.json.bak.<ts>installed_plugins.json.bak.<ts>known_marketplaces.json.bak.<ts>
Keeps the most recent backup per file (sorted lexically — the ISO
timestamp is monotonic) and removes the rest. Does not touch user-named
backups like settings.json.bak-pre-v0.1.8. Idempotent — if at most one
backup exists per file, prints "nothing to clean" and exits 0.
Defaults to user-level (~/.claude/); pass --project for project-level
(cwd's .claude/).
--purge-runtime
Pass --purge-runtime to also wipe the plugin's runtime state files.
v0.4.x+ Per-Project Layout: every <projectHash>/ subdirectory under
state/ is walked and the following files inside it are removed:
cache.json— the on-disk fetch cache (60s TTL)diagnostics.jsonl— the persistent diagnostics log (only exists whenCREDITGAUGE_DIAGNOSTICS_ENABLE=1has been set)*.jsonl— the per-session token-sample files backing them_acc*/m_sum*module family.
After wiping all runtime files inside a project dir, the now-empty
directory itself is removed (via rmdir — fails safely on non-empty
dirs). Project dirs that still contain non-runtime files are left in
place.
state/upstream-cmd.{sh,txt} and state/config.json are NEVER
purged — they're managed by install/uninstall, not by per-tick IO,
and wiping them would break future uninstalls.
These files are user-level only — --purge-runtime is ignored
under --project (the state dir has no project-level counterpart).
Combined usage: clean.sh --purge-runtime --dry-run to preview.
The uninstall slash command (/creditgauge:uninstall) calls
this script as its final step (without --purge-runtime), so explicit
cleanup of backups is usually unnecessary after a fresh uninstall.
--purge-runtime is opt-in because the runtime state contains your
diagnostics history — only wipe when you actually want it gone.
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.
- 1mo ago First seen · 61 lines · 17 tokens per session scan A e55094ccafc7
clean is a command published in the GitHub repository cwf818/topgauge (2 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 616 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
resume
Continue a cli-dispatch worker session with a follow-up prompt (auto-detects backend).
configure
Configure HUD display options (layout, language, presets, display elements) while preserving advanced manual overrides.
configure
Adjust what ClaudeMeter shows in your statusline.
debug
Diagnose balance-hud — wiring, provider, model name, balance snapshot, daemon and watchdog state, plus a simulated statusline render.
doctor
Diagnose what is busting Claude Code's DeepSeek prefix cache.
status
Show Permafrost's live DeepSeek cache hit rate and dollar savings.