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.
git clone --depth 1 https://github.com/goldenwo/claude-state-driftWrote 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/goldenwo/claude-state-drift/stats)<a href="https://agentmods.dev/commands/goldenwo/claude-state-drift/stats"><img src="https://agentmods.dev/badge/commands/goldenwo/claude-state-drift/stats.svg" alt="Measured on agentmods" 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 | $0.00065 | $0.00278 |
| Opus 5 | $0.00032 | $0.00139 |
| Sonnet 5 | $0.00013 | $0.00056 |
| Haiku 4.5 | $0.00006 | $0.00028 |
Grade A, and why
stats 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 7d 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
Run where-am-i --stats (on PATH when the plugin is active) against the current project. It reads the local .claude/.hook-log.jsonl (present only when CLAUDE_HOOK_LOG=1 is set) plus .claude/state-history.jsonl, and prints an operational stats block: reach (sessions + window), activity (orientations, focus re-injections, commit and staleness nudges), cost (token estimate p50/p95), nudge-to-update conversion, and staleness-resolution. Pass --stats --json instead for a machine-readable form. Everything is computed on the user's machine; nothing is sent anywhere.
If the hook log is absent, the block says "no telemetry yet" — tell the user to set CLAUDE_HOOK_LOG=1 and run some sessions first so data can accumulate. These are operational metrics (activity + cost), not an effectiveness measure.
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.
- 7d ago First seen · 9 lines · 65 tokens per session scan A 7334236ae8f9
stats is a command published in the GitHub repository goldenwo/claude-state-drift (1 stars, last pushed 20d ago), licensed MIT. It adds 65 tokens to every session and 278 once invoked, about $0.0003 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
learn
Force claude-smart to extract learnings from this session now.
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
audit-plugin
Audit plugin skills, commands, and agents for structure, size, and naming issues.