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 OutlineDriven/odin-claude-plugin --skill diagram-contractgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/diagram-contract)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/diagram-contract"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/diagram-contract/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/outlinedriven/odin-claude-plugin/diagram-contract"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/diagram-contract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 69 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00062 | $0.01231 |
| Opus 5.5 | $0.00025 | $0.00492 |
| Sonnet 5.5 | $0.00012 | $0.00246 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
diagram-contract 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 1mo 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Every diagram that lands in a document follows one shape: a text DSL source beside the document and a committed SVG rendered from it. This skill picks the tool, applies the house palette, and produces both artifacts so the image carries on github.com.
Pick the tool
Reach up the table only when the default cannot carry the domain. The default is the first row.
| Purpose | Tool |
|---|---|
| Structure, class, relations, small-to-medium flow, state, timeline | nomnoml (default) |
| Architecture, system, module dependencies, container maps | D2 |
| Very large dense DAG, hundreds of nodes | Graphviz DOT |
| Byte, bit, or on-disk layout | bytefield-svg |
| Quantitative chart, only with sourced real figures | Vega-Lite |
Author it
Five steps, each with a checkable done condition.
- Choose the shape. A comparison, trade-off, or decision matrix is a Markdown table. For a quantitative comparison whose real numbers cannot be sourced, a table is the required form, not a chart. Done when the choice between table and diagram is made and stated.
- Write the source into
assets/<kebab-slug>.<ext>beside the document that will embed it, opening with the house header below when the tool is nomnoml. Done when the file exists on disk and, for nomnoml, the header is the first block in it. - Render with the matching command under Render commands. Done when the command exits zero and the SVG exists beside its source.
- Embed as
followed directly by a one-line>caption carrying the key message. Done when both lines are present, the alt text is a label rather than the word "diagram", and the caption states what the image means rather than restating its title. - Commit source and SVG together. Done when both paths are staged. Never commit one without the other; the pair is the contract.
House header
Open every nomnoml source with this header verbatim. It sets direction, background, spacing, stroke, and the named styles accent, blue, green, neutral, and ghost.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 85 lines · 62 tokens per session scan A 10341a3017a4
diagram-contract is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (39 stars, last pushed 27d ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,231 once invoked, about $0.0002 per session on Opus 5.5. 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
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…