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 prototypegit 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/prototype)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/prototype"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/prototype.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.03100 |
| Opus 5 | $0.00018 | $0.01550 |
| Sonnet 5 | $0.00007 | $0.00620 |
| Haiku 4.5 | $0.00004 | $0.00310 |
Grade A, and why
prototype 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 yesterday.
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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prototype
Contract
| Field | Bound contract |
|---|---|
| Trigger | Explicit model invocation: one design question needs a cheap logic or UI experiment, including a state-model, logic, or data-shape question a human checks by pressing buttons and watching state change, even when the driver is a non-developer. |
| Authority | Reversible local: writes throwaway prototype artifacts and their verdict on a throwaway branch off main; may fold the validated decision into the named real-code target as a working-tree edit the user commits through their normal flow; rollback is abandoning the throwaway branch or restoring its commits. Never push, delete existing work, or change production rendering. No remote mutation. |
| Side effect | Write one throwaway prototype artifact and its verdict off the main branch; that branch is the evidence, not a delivery target. |
| Done | The question is answered in one line and the decision is folded into the real work. |
Inputs
- Question (required): the design question being answered, drawn from the user's prompt or surrounding code. If the question is genuinely ambiguous and the user is reachable, ask before routing.
- Context (required): the surrounding code or page that frames the question. Determines whether to route to LOGIC or UI.
- LOGIC mode also takes: the relevant state, actions, domain terms, and legal-transition rules; a path for the throwaway HTML file; representative scenarios or enough domain rules to derive a happy path, a tricky edge case, and an illegal-action attempt; the main branch the throwaway branch is based on; and a real-code target, required only after the human validates the module.
Procedure
Route
Route before writing because LOGIC and UI variants require different artifact structures.
- Classify the question:
- Logic: state machine, edge case, data shape, reducer, API contract, or "does this feel right" → use the LOGIC procedure below.
- UI: what something should look like, layout, information hierarchy, or "what should this look like" → use the UI procedure below.
- If ambiguous and the user is not reachable, default: backend module → LOGIC; page or component → UI. State the assumption at the top of the artifact. Done when: the question is classified as LOGIC or UI, or the ambiguity default is stated and recorded on the artifact.
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.
- yesterday First seen · 110 lines · 36 tokens per session scan A a21fbd2a2213
prototype is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), licensed Apache-2.0. It adds 36 tokens to every session and 3,100 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 2026-09-06.
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…