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 overlay-and-fitgit 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/overlay-and-fit)<a href="https://agentmods.dev/skills/cruxible-ai/cruxible/overlay-and-fit"><img src="https://agentmods.dev/badge/skills/cruxible-ai/cruxible/overlay-and-fit/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/overlay-and-fit"><img src="https://agentmods.dev/badge/skills/cruxible-ai/cruxible/overlay-and-fit.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 | $0.00043 | $0.02332 |
| Opus 5 | $0.00022 | $0.01166 |
| Sonnet 5 | $0.00009 | $0.00466 |
| Haiku 4.5 | $0.00004 | $0.00233 |
Grade A, and why
overlay-and-fit 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overlay And Fit
Use this skill when the user wants to start from a published reference state and fit it to a local use case with the least friction. You are extending a published Crux with a local overlay, not authoring one from scratch.
This is the reference-state path, not the greenfield path. Start from the inherited state, use the applied kit if one exists, and only add local config or code when the current overlay is not enough.
If you are not sure whether the current workspace is already an overlay, check first:
cruxible state status
If it reports upstream tracking metadata, continue in the current workspace.
If it says the instance is not tracking an upstream published state, create an overlay first:
cruxible state create-overlay --state-ref <alias> --root-dir <root_dir>
Here, <root_dir> is the workspace root directory that will contain the local config.yaml and the .cruxible/ instance directory. It is not the .cruxible/ directory itself.
If that state has a configured default kit, its local files will be copied into the workspace automatically. This usually means the overlay-specific config.yaml plus any companion workspace files that kit needs, such as local provider code, artifacts or seed data, helper files, or other local starting material. The exact kit shape may vary. Use --kit <kit> to override the default kit, or --no-kit for a bare overlay.
Cruxible Terms
canonicalbehavior means deterministic graph-building or refresh behavior whose results can be written directly into stategovernedbehavior means judgment-based behavior that should go through proposal, review, and resolution before it becomes durable stateproposal workflowsare the non-canonicalworkflowsthat produce reviewable candidates or groups instead of writing directly into statenamed_queriesare the user-facing query entry points the state exposesprovidersare the code or model-backed steps thatworkflowscall
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 · 242 lines · 43 tokens per session scan A ab2ececb6f45
overlay-and-fit is a skill published in the GitHub repository cruxible-ai/cruxible (17 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 2,332 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 2026-08-30.
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.