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 cruxible-ai/cruxible --skill create-stategit clone --depth 1 https://github.com/cruxible-ai/cruxibleWrote 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/cruxible-ai/cruxible/create-state)<a href="https://agentmods.dev/skills/cruxible-ai/cruxible/create-state"><img src="https://agentmods.dev/badge/skills/cruxible-ai/cruxible/create-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/skills/cruxible-ai/cruxible/create-state"><img src="https://agentmods.dev/badge/skills/cruxible-ai/cruxible/create-state.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00027 | $0.02039 |
| Opus 5 | $0.00014 | $0.01019 |
| Sonnet 5 | $0.00005 | $0.00408 |
| Haiku 4.5 | $0.00003 | $0.00204 |
Grade A, and why
create-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 11d 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create State
Use this skill when a user wants to turn new data into a usable Cruxible state. You are authoring a Crux — the governed, executable artifact of the user's domain knowledge — so treat every stage below as artifact construction, not config editing: what you produce will be reviewed, versioned, and relied on by other agents.
If the source files are messy, run prepare-data first.
Work in stages. Do not try to design the graph, workflows, queries, and review loop all at once.
Generated config views
Do not rely on YAML alone when drafting or reviewing a state. At each major config checkpoint, generate canonical views from the config and use those views as the review surface.
Use inline output for fast review when the agent harness can render Mermaid:
uv run cruxible config views --config config.yaml --view all
Also update durable README marker blocks so CLI and non-GUI harnesses can inspect the same generated views:
uv run cruxible config views --config config.yaml --update-readme README.md
If the config uses extends, render the runtime composed view for
onboarding/review surfaces:
uv run cruxible config views --config config.yaml --runtime --view all
uv run cruxible config views --config config.yaml --runtime --update-readme README.md
Everything between CRUXIBLE:BEGIN / CRUXIBLE:END markers is code-owned
structural output from the config. Authored prose may explain intent,
tradeoffs, open questions, and operating guidance, but it must not replace or
contradict the generated structural view. Do not hand-author alternate Mermaid
diagrams when a generated view exists.
When iterating the config toward its final shape, explicitly direct the user to the generated README views as the primary way to understand the current system. The YAML remains the execution source of truth, but the README's generated ontology, workflow, governed relationship, and query sections are the review surface for human decisions. Before asking the user to approve graph shape, workflow sequencing, governed boundaries, or query surfaces, update the README marker blocks and point them to the relevant generated section.
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.
- 11d ago First seen · 230 lines · 27 tokens per session scan A f1aa44f18edc
create-state is a skill published in the GitHub repository cruxible-ai/cruxible (17 stars, last pushed 3d ago), licensed Apache-2.0. It adds 27 tokens to every session and 2,039 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 2026-08-30.
Other skills, from other repositories
rijksmuseum-mcp-plus
Research workflows for the Rijksmuseum MCP+ server, addressing Dutch arts, crafts, and history across the museum's holdings. Capabilities include keyword, structured, and semantic text search, AI-driven image analysis, geospatial queries, collection statistics, Iconclass-driven iconographic discovery, AAM/CMOA-aligned…
en-quire
Instructions for using en-quire MCP tools to read, search, edit, and manage markdown and YAML documents. Use this skill whenever working with .md, .mdx, .yaml, or .yml files — SOPs, skill files, session memory, codex articles, specs, and configuration files. Covers section-addressed editing, structural search, YAML…
code-graph
Query the Code Graph knowledge graph for this codebase. Use when the user asks about code structure, call relationships, dependencies, blast radius, or wants to run SPARQL queries against the project graph. Requires the backend and MCP server to be running.
Agent Audit Trail
Append-only, hash-chained audit log for AI agents. Records agent actions, tool calls, decisions, and external writes with provenance, timestamps, and sha256 chain integrity. Designed for compliance with EU AI Act Article 12 automatic event recording requirements for high-risk AI systems.
governance-hotl
OpenMesha governance — fail-closed policy, HOTL for irreversible actions, audit log inspection. Use when reviewing denials, escalations, or audit trails.
governance-audit
Inspect Server OS policy decisions, capability grants, and the audit log.