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/creditgauge/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/creditgauge/clean-journal)<a href="https://agentmods.dev/commands/cwf818/creditgauge/clean-journal"><img src="https://agentmods.dev/badge/commands/cwf818/creditgauge/clean-journal/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/creditgauge/clean-journal"><img src="https://agentmods.dev/badge/commands/cwf818/creditgauge/clean-journal.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 | $0.00018 | $0.00286 |
| Opus 5 | $0.00009 | $0.00143 |
| Sonnet 5 | $0.00004 | $0.00057 |
| Haiku 4.5 | $0.00002 | $0.00029 |
Grade A, and why
clean-journal 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 9d 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.
What it actually says
creditgauge :clean-journal
Targets the append-only JSONL token-sample history files at
state/<projectHash>/<sessionId>.jsonl. These accumulate over
time and can use significant disk space.
Behavior
- Default: removes
.jsonlfiles older than 7 days --days <N>: remove files older than N days--all: remove ALL.jsonljournal files (use with caution)
Safety
- Only removes files matching
*.jsonlunderstate/<projectHash>/ - Never touches
diagnostics.jsonl,cache.json, orstate.json --dry-runpreviews what would be removed without deleting
Examples
# Preview what files older than 7 days would be removed
/creditgauge:clean-journal --dry-run
# Remove files older than 30 days
/creditgauge:clean-journal --days 30
# Remove every journal file
/creditgauge:clean-journal --all
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.
- 9d ago First seen · 37 lines · 18 tokens per session scan A b14695aba9a1
clean-journal is a command published in the GitHub repository cwf818/creditgauge (2 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 286 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.
Other commands, from other repositories
ponytail-help
Quick reference for ponytail levels, skills, and commands.
explore
Fast codebase exploration with Antigravity's agy CLI (Gemini 3.7 Flash, read-only). EXPERIMENTAL.
statusline
Show the governor fleet in your Claude Code statusline. Explicit, opt-in, and chains — it never replaces an existing statusline.
takeoff
Create, resume, or clear a session hand-off baton (one per work line).
kill
Stop a running cli-dispatch worker session.
tasks
Inspect Modellix task status and recover tasks after a timeout or unknown submission.