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 to-specgit 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/to-spec)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/to-spec"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/to-spec/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/to-spec"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/to-spec.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 | $0.00058 | $0.01106 |
| Opus 5 | $0.00029 | $0.00553 |
| Sonnet 5 | $0.00012 | $0.00221 |
| Haiku 4.5 | $0.00006 | $0.00111 |
Grade A, and why
to-spec 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 5d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
To spec
Contract
| Field | Bound contract |
|---|---|
| Trigger | Settled decisions need synthesis into an implementation spec. |
| Authority | Reversible local: write only a named local spec file; the rollback path is deleting that file. |
| Side effect | Writes an agent-ready specification file locally and stops before publishing or distributing it; a human performs any publication. |
| Done | Problem, solution, stories, decisions, tests, and exclusions are agent-ready in a verified local specification file; publication remains an unexecuted human handoff. |
Inputs
- Conversation context. The current conversation must contain settled decisions: what is being built, why, and how completion will be judged. If the conversation lacks settled decisions, stop and state what is missing.
- Codebase state. Explore the repository to understand the current state. Use the project's domain glossary vocabulary throughout the spec and respect any ADRs in the area being touched.
- Optional: CONTEXT.md or domain docs. If present, read them for vocabulary and constraints. Do not require them.
Refusals
- Will not interview the user or open a new round of questioning — synthesize what has already been decided.
- Will not fabricate decisions or fill gaps with assumptions.
- Will not publish, distribute, or assign labels — publication is a human handoff.
- Will not proceed to spec writing until the user confirms the identified seams.
Procedure
- Explore the repository to understand the current state of the codebase if not already done. Identify the project's domain vocabulary and any ADRs in the relevant area. Done when: the codebase state and domain vocabulary are understood.
- Identify the seams at which the feature will be tested. Prefer existing seams to new ones, and use the highest existing seam possible. If a new seam is needed, propose it at the highest practical point. Fewer seams across the codebase are better; the ideal number is one. Done when: the testing seams are identified.
- Present the identified seams to the user and confirm they match expectations. Do not proceed until the user confirms. Done when: the user confirms the seams.
- Synthesize the spec from the conversation context, codebase understanding, and confirmed seams. Do not interview the user or open a new round of questioning. Capture what has already been decided. Done when: the spec content is synthesized from settled decisions.
- Write the spec to
docs/specs/<feature-slug>-spec.mdusing the template below. Done when: the spec file is written to disk. - Verify the written file contains all seven sections populated with substantive content. If any section is empty or stubbed, fill it before declaring done. Done when: all seven sections are substantive.
- Stop. Do not publish, distribute, or assign labels. Report the file path and that publication is a human handoff. Done when: the file path is reported and no publication action is taken.
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.
- 5d ago First seen · 104 lines · 58 tokens per session scan A d61b2fe424b1
to-spec is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed 2d ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,106 once invoked, about $0.0003 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 2026-09-04.
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…
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
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…