agentmods.dev

reset

reset is a command for coding agents from cwf818/creditgauge. It costs 30 tokens per session (488 once invoked), scanned A, original, MIT.

A project-only command that removes three runtime cache files while preserving diagnostics, installation settings, and token-sample history.

In plain words
What is it for?
Fixing status displays or accumulated statistics that show outdated or incorrect numbers after an upgrade, schema change, or failed update.
Why use it?
It clears stale or corrupted cached values without deleting data needed to uninstall, reconfigure, or review past token samples.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the creditgauge plugin — 7 commands shipped together

not rated 2 today A scan 30 tokens original MIT
View the source file cwf818/creditgauge
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 commands/cwf818/creditgauge/reset
Clone the repo
git clone --depth 1 https://github.com/cwf818/creditgauge

Or install creditgauge, the plugin that ships this one along with the rest of its 7 commands.

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 reset

README.md
[![agentmods](https://agentmods.dev/badge/commands/cwf818/creditgauge/reset.svg)](https://agentmods.dev/commands/cwf818/creditgauge/reset)
Your own site
<a href="https://agentmods.dev/commands/cwf818/creditgauge/reset"><img src="https://agentmods.dev/badge/commands/cwf818/creditgauge/reset.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 488 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00030 $0.00488
Opus 5 $0.00015 $0.00244
Sonnet 5 $0.00006 $0.00098
Haiku 4.5 $0.00003 $0.00049

Measured 5d ago against content hash 115bd97318d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reset 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 5d 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.

commands/reset.md · 49 lines

What it actually says

creditgauge :reset

Targets 3 runtime cache files for the current project only (other projects' caches are never touched):

  • cache.json — provider data cache (60s TTL on-disk shadow; top-level state/cache.json shared across projects — per-project isolation is via <projectHash>: key prefix, not by file split)
  • state.json — per-project tick / acc / prev-tick state (state/<projectHash>/state.json)
  • cache.stat.json — cross-project sum/avg stat cache (regenerated on next read; 300s TTL gate either way; top-level state/cache.stat.json)

When to use this:

  • The statusline shows stale or wrong numbers (likely a corrupt cache.json from a provider schema change).
  • m_acc* / m_sum* modules show weird values (stale state.json from an upgrade or a partially-failed tick).
  • cache.stat.json is suspected of being stale or corrupt (rare; m_statTtlStatus should surface this).

What is INTENTIONALLY preserved:

  • state/upstream-cmd.{sh,txt} and state/config.json — install / user state. Wiping these would break future uninstalls.
  • <sessionId>.jsonl — append-only token-sample history (the data source for m_sum* modules).
  • diagnostics.jsonl — append-only warning log.
  • <otherProjectHash>/** — never touched.

Pass --dry-run to preview what would be removed without changing anything.

Use clean.sh --purge-runtime to also wipe diagnostics + .jsonl, or uninstall.sh to wipe everything. :reset is the targeted version that keeps your history.

Execute the reset script with whatever arguments were passed:

"${CLAUDE_PLUGIN_ROOT}/scripts/reset.sh" $ARGUMENTS
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. 5d ago First seen · 49 lines · 30 tokens per session scan A 115bd97318d2

Subscribe to this mod's changes

reset is a command published in the GitHub repository cwf818/creditgauge (2 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 488 once invoked, about $0.0002 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.

balanceclaude-codeclaude-code-plugincredit-plandeepseekminmax
Related

Other commands, from other repositories

clean

Remove old .bak. backup files, keeping only the most recent per file.

cwf818/topgauge · 17 tokens

uninstall

Uninstall creditgauge (CreditGauge), restore settings.json, and wipe the plugin's cache, marketplace, and loader rows.

cwf818/topgauge · 25 tokens

clean-cache

Remove stale version directories under the plugin cache, keeping only the newest.

cwf818/topgauge · 13 tokens

install

Install the creditgauge (CreditGauge) statusline wrapper into Claude Code's settings.json (for uninstall use the dedicated :uninstall slash command).

cwf818/topgauge · 30 tokens

review

Run a Pi code review against local git state.

Agents365-ai/pi-plugin-cc · 9 tokens

adversarial-review

Run a Pi review that challenges the implementation approach and design choices.

Agents365-ai/pi-plugin-cc · 12 tokens