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.
npx skills add hazarsozer/crucible-cc --skill historygit clone --depth 1 https://github.com/hazarsozer/crucible-ccWrote 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/skills/hazarsozer/crucible-cc/history)<a href="https://agentmods.dev/skills/hazarsozer/crucible-cc/history"><img src="https://agentmods.dev/badge/skills/hazarsozer/crucible-cc/history/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/skills/hazarsozer/crucible-cc/history"><img src="https://agentmods.dev/badge/skills/hazarsozer/crucible-cc/history.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 | $0.00037 | $0.00738 |
| Opus 5 | $0.00018 | $0.00369 |
| Sonnet 5 | $0.00007 | $0.00148 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
history 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/crucible:history — Review History
List past Crucible reviews and offer to show one in full. Reviews are stored at .review/reports/<review_id>.md in the project root.
Steps
-
List reports. Find every file under
.review/reports/matching the pattern*.md. If none exist, print:No past reviews found. Run /crucible to create one.and exit.
-
Parse metadata from each report. For each file, extract:
review_id— from the filename (strip.md).final_score— from the line beginning with**Score:**(or fall back toScore:if formatting differs).final_verdict— from the line beginning with**Verdict:**.scope_description— from the H1 line# Crucible Review — <description>.completed_at— from the metadata line_Review ID: ... · Generated: <timestamp>_.
If parsing fails on any field, fall back to
?for that field. -
Sort reports newest-first by
completed_atif available, else by filename (which encodes the timestamp prefix). -
Print a table. Use fixed-width columns. Truncate long descriptions to 40 chars with
….# Review ID Score Verdict Scope ───────────────────────────────────────────────────────────────────────────────── 1 2026-05-10-1430-auth-refactor 7.1 conditional_approval auth module rewrite 2 2026-05-09-1620-api-rewrite 8.4 approved /api/v2 endpoints ... -
Prompt for selection.
Show full report for which # (or `n` to exit)?- If the user enters a number that maps to a row, print the full contents of that report file.
- If the user enters
n,no,exit,quit, or empty, exit silently. - If the input is invalid, print
Not a valid selection.and exit.
-
For partial reports. Files matching
*-PARTIAL.md(incomplete runs) appear in the listing with a⚠️prefix in theVerdictcolumn to make it clear they don't represent a complete pipeline run.
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.
- 12d ago First seen · 58 lines · 37 tokens per session scan A 6eb843c84876
history is a skill published in the GitHub repository hazarsozer/crucible-cc (4 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 738 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.
Other skills, from other repositories
refactoring-patterns
Apply named refactoring transformations to improve code structure without changing behavior. Use when the user mentions "refactor this", "code smells", "extract method", "replace conditional", "technical debt", "move method", "inline variable", "decompose conditional", or "clean up this messy code". Also trigger when…
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
pr
Comprehensive PR/issue review - analyzes architecture, tests, identifies unrelated changes mixed in, drafts review comment or issue comment. Use when user asks to review a PR, check a PR, look at PR changes, or comment on an issue.
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…
brooks-audit
Architecture audit that maps module dependencies, checks layering integrity, and flags structural decay across a codebase, drawing on twelve classic engineering books. Triggers when: user asks to audit architecture, review folder/module structure, check for circular imports, understand how the codebase is organized…