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 type-drivengit 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/type-driven)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/type-driven"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/type-driven/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/type-driven"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/type-driven.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 | $0.00044 | $0.00849 |
| Opus 5.5 | $0.00018 | $0.00340 |
| Sonnet 5.5 | $0.00009 | $0.00170 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
type-driven 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Type-driven development
Contract
| Field | Bound contract |
|---|---|
| Trigger | The work is modeling a domain, encoding a state machine, hardening an API boundary, making invalid states unrepresentable, or parsing instead of validating. |
| Authority | Reversible local: writes only domain types, public signatures, and affected callers and tests; rollback is version control or undo. No remote mutation. |
| Side effect | Rewrites domain types, public signatures, and affected callers and tests to the new algebraic model. |
| Done | Invalid states are unconstructible, matches are exhaustive, boundaries parse, and no scattered post-hoc validation remains. |
Inputs
Required: the domain problem, data model, or API surface to encode. Optional: existing types or callers to refactor.
Refusals
- Will not add runtime guards to fix a type-design failure: fix the type design.
- Will not add a wildcard arm to silence a non-exhaustive match: add the missing variant.
- Will not proceed with type holes or incomplete bodies.
- Will not use this approach when the language lacks ADTs, sealed hierarchies, or equivalent sum-type support: skip and report.
Procedure
- Plan. State the domain in one paragraph. List all valid states, all invalid states, and every operation with its preconditions and postconditions. If any operation is partial, mark it as such. Done when: the domain is stated with valid states, invalid states, and operations listed.
- Design types first. For each invalid state, write a type that the compiler prevents. Use ADTs, phantom types, branded types, newtype wrappers, sealed hierarchies, or opaque types, whichever the language supports. Do not write implementation bodies until all types compile. Done when: all types compile and every invalid state is unrepresentable.
- Parse at boundaries. For every untrusted input (external data, deserialization, FFI, user input), write a
parseconstructor that returns the new type. Do not returnbooland defer validity to callers. Done when: every untrusted input boundary has a parse function returning the new type. - Exhaustive matching. Encode state machine transitions as exhaustive
match/switch/visiton the sum type. Compiler warnings on incomplete arms are failures. Done when: every state-machine transition is an exhaustive match with no wildcard arms. - Verify. Run the language's strict type checker and exhaustiveness check. Fix the type design, not the implementation, when the checker reports an illegal state is representable. Done when: the type checker and exhaustiveness check pass.
- Build. Run the full target build. Implement the bodies guided by the types. Done when: the target build passes.
What ships with it
4 files 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 Changed · -21 tokens per session 2b331c42fc4e
- 1mo ago First seen · 52 lines · 65 tokens per session scan A 1d4053348f88
type-driven is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (37 stars, last pushed 21d ago), licensed Apache-2.0. It adds 44 tokens to every session and 849 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 2026-09-04.
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…
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…
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…