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 agentmods add skills/outlinedriven/odin-gemini-cli-extension/type-drivennpx skills add OutlineDriven/odin-gemini-cli-extension --skill type-drivengit clone --depth 1 https://github.com/OutlineDriven/odin-gemini-cli-extensionWrote 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-gemini-cli-extension/type-driven)<a href="https://agentmods.dev/skills/outlinedriven/odin-gemini-cli-extension/type-driven"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/type-driven.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00036 | $0.01322 |
| Opus 5 | $0.00018 | $0.00661 |
| Sonnet 5 | $0.00007 | $0.00264 |
| Haiku 4.5 | $0.00004 | $0.00132 |
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 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.
This is a copy
89% identical to type-driven — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Type-driven development
Types encode the specification -- design from requirements before implementation. Make illegal states unrepresentable (Yaron Minsky). Parse, don't validate (Alexis King). For parsed opaque domain types within trusted boundaries, if the type compiles, the value is valid.
Modern insight (2025): "Encode invariants in types, not runtime checks" is the evolved formulation. Type richness should match risk -- start simple, add complexity where bugs actually occur. Types serve AI-assisted development: they communicate intent better than comments and reduce LLM hallucinations.
See patterns for language-specific refined types, state machine techniques, and language-specific validation gates. See examples for brief "parse, don't validate" patterns per language. See formal-tools for dependent type systems and verification tools.
Parse, Don't Validate
- Validate: Check if data is valid -> return bool -> caller must remember check happened. Proof is lost.
- Parse: Transform untrusted data into typed value that proves validity -> return new type. Proof is preserved.
- Consequence: Once parsed into an opaque domain type, internal code within trusted boundaries receives typed values and should not re-validate the same invariant. Note: deserialization, casts, FFI, and unsafe escape hatches can bypass the type system -- runtime checks remain necessary at those boundaries.
- Alexis King clarification: Newtypes are convenient but encapsulation-dependent. Best for simple invariants. Phantom types and branded types provide richer guarantees.
Making Illegal States Unrepresentable
- ADTs / Discriminated Unions: Model business rules as sum types.
Payment = Pending | Processing { id } | Success { id, amount } | Failed { reason }. Compiler ensures every case handled. - Phantom/Branded Types: Prevent accidental mixing of structurally identical but semantically different values (UserId vs PostId). Zero runtime cost.
- Typestate Pattern: Encode valid method sequences in types.
Client<Disconnected>has noread()method. Compile error if called wrong. - Newtype Wrappers: Lightweight validated wrappers.
EmailAddress(String)with private constructor + validation innew().
What ships with it
3 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.
- yesterday First seen · 115 lines · 36 tokens per session scan A 49333b6dd4ef
type-driven is a skill published in the GitHub repository OutlineDriven/odin-gemini-cli-extension (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,322 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to type-driven, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
design
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…
askme
Verbalized Sampling (VS) protocol for intent exploration before planning, mode-aware. Default exhaustive runs full VS; collaborative runs tip-sharing dialogue; adversarial walks the design tree one fork at a time. Auto-detects from phrasing ("help me refine" → collaborative, "poke holes" → adversarial); override via…
grill-ai-mastery
Hybrid interview that probes AI-engineering mastery by tip-vocabulary depth — entity referencing, loop closure, observability, harness improvement — not by token usage or LOC. Start collaborative (two-way tip exchange), escalate to adversarial probing when depth is lacking. Trigger when the user says "interview me on…
grill-me
Adversarial relentless interview against any plan or design until shared understanding is reached. Walk the decision tree, resolve dependencies one answer at a time, recommend a default per question. Trigger when the user says "grill me", "stress-test this", "interview me about this design", or otherwise asks for…
fix
Polymorphic iterative repair loop — accept a verifier failure, structured findings (review/resolve/triage-issue), or a bug description; modify→verify→keep on green, auto-revert on guard regression, until clean or iteration cap. Use when the user says "fix", "make it pass", or "apply the findings", or hands an artifact…
git-branchless
Enforce idiomatic git-branchless during planning and executing tasks — detached-HEAD-first work, in-memory rebase via git move, event-log recovery via git undo, deferred branch creation, speculative-merge git sync for base updates. Use when planning or executing multi-commit work, history rewrites, stack edits…