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/smshahbaj/crucibleWrote 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/smshahbaj/crucible/review)<a href="https://agentmods.dev/commands/smshahbaj/crucible/review"><img src="https://agentmods.dev/badge/commands/smshahbaj/crucible/review.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 | $0.00026 | $0.00119 |
| Opus 5 | $0.00013 | $0.00060 |
| Sonnet 5 | $0.00005 | $0.00024 |
| Haiku 4.5 | $0.00003 | $0.00012 |
Grade A, and why
review 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
Use the crucible skill on the current request.
Routing:
- default: adaptive
- QUICK: lowest-cost sanity check
- REVIEW: independent second opinion
- DEEP: high-stakes pressure test
- VERIFY: evidence-first
- REDTEAM: failure-first
- COMPARE: option comparison
Never force a fixed number of agents. Finish with a concise action-oriented result unless the user asks for detail.
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 · 18 lines · 26 tokens per session scan A 0b9b3586bd3e
review is a command published in the GitHub repository smshahbaj/crucible (9 stars, last pushed 14d ago), licensed MIT. It adds 26 tokens to every session and 119 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
release
Generate changelog, bump version, and create git tag.
typescript-dev
Start TypeScript development workflow with architecture, implementation, review, and testing phases.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
validate
Mechanically validate the sonu plugin repo before a PR — manifest sync, YAML frontmatter, shell-fence syntax, named-source and AI-attribution scans, cross-reference integrity, skill reachability. Only meaningful inside the claude-plugins repo; in any other repo, say so and stop.
generate-report
Generate a professional HTML report from assessment results in the conversation.
data-flow-analysis
Trace how data flows through the system from input to output.