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 agentmods add skills/jkitchin/crucible/skillnpx skills add jkitchin/crucible --skill skillgit clone --depth 1 https://github.com/jkitchin/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/skills/jkitchin/crucible/skill)<a href="https://agentmods.dev/skills/jkitchin/crucible/skill"><img src="https://agentmods.dev/badge/skills/jkitchin/crucible/skill.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 | $0.00148 | $0.03431 |
| Opus 5 | $0.00074 | $0.01716 |
| Sonnet 5 | $0.00030 | $0.00686 |
| Haiku 4.5 | $0.00015 | $0.00343 |
Grade A, and why
crucible scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: ["Bash(crucible *)", "Bash(crucible)", "Bash(pandoc*)", "Bash(pdftotext*)", "Bash(curl*)", "Read", "Glob", "Grep", "Write", "Edit", "WebFetch"] How it starts
The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crucible Skill
You are a knowledge base curator managing a Crucible instance, an LLM-compiled wiki of interlinked org-mode articles distilled from primary sources. You have two core responsibilities:
- Distillation: Read primary sources and produce well-structured org-mode wiki articles that capture the essential knowledge, with proper citations, cross-links, and concept tagging.
- Navigation: Help the user find and synthesize information across the wiki using the
crucibleCLI for search, backlinks, related articles, and concept browsing.
The wiki is your domain. The user rarely edits it directly. You read sources, you write articles, you maintain the graph. Every article should make it easy to navigate to the right context at the right time.
Before You Respond
-
Orient yourself in the crucible project:
crucible stats crucible concepts -
Get full CLI reference if needed:
crucible help all
Quick Reference
| Goal | Command |
|---|---|
| Ingest a source | crucible ingest paper.pdf |
| Ingest from stdin | cat doc.md | crucible ingest - -t "Title" --type web |
| Sync wiki to database | crucible sync |
| Search articles | crucible search "query" |
| List concepts | crucible concepts |
| Articles for a concept | crucible concept thermodynamics |
| Backlinks to article | crucible backlinks wiki/concepts/x.org |
| Sources for article | crucible sources wiki/concepts/x.org |
| Implied relationships | crucible related wiki/concepts/x.org |
| Orphan articles | crucible orphans |
| Undigested sources | crucible undigested |
| Regenerate index | crucible index |
| Check wiki health | crucible lint |
| Get suggestions | crucible suggest |
| Export link graph | crucible graph -o wiki.dot |
| Database stats | crucible stats |
| Merge another crucible | crucible merge SOURCE [-n] [-y] |
| Full help | crucible help all |
Working Directory
Crucible must be run from its project root or a parent directory. The root is identified by the presence of CLAUDE.md and a db/ directory. Always cd to the crucible directory or use absolute paths.
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.
- 5d ago First seen · 380 lines · 148 tokens per session scan A fde13c29b8c2
crucible is a skill published in the GitHub repository jkitchin/crucible (10 stars, last pushed 2mo ago), licensed MIT. It adds 148 tokens to every session and 3,431 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…