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/update-state)<a href="https://agentmods.dev/commands/goldenwo/claude-state-drift/update-state"><img src="https://agentmods.dev/badge/commands/goldenwo/claude-state-drift/update-state/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/goldenwo/claude-state-drift/update-state"><img src="https://agentmods.dev/badge/commands/goldenwo/claude-state-drift/update-state.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 | $0.00078 | $0.00213 |
| Opus 5 | $0.00039 | $0.00106 |
| Sonnet 5 | $0.00016 | $0.00043 |
| Haiku 4.5 | $0.00008 | $0.00021 |
Grade A, and why
update-state 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 8d 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
Invoke the Skill tool with claude-state-drift:update-state against the current project. Do not inline or paraphrase the procedure — defer to the skill for the full contract (inspect current state + detect candidate transitions + draft a precise edit + show diff + wait for approval + validate after write).
If .claude/state.json doesn't exist in the current project, report that and skip (no enforcement on uninstrumented projects).
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.
- 8d ago First seen · 9 lines · 78 tokens per session scan A b1fc1b767b7a
update-state is a command published in the GitHub repository goldenwo/claude-state-drift (1 stars, last pushed 21d ago), licensed MIT. It adds 78 tokens to every session and 213 once invoked, about $0.0004 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.
check-dev
Type-check a Z specification with fuzz.
adr-supersede
Create a new ADR that supersedes an existing one.