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 spec-driven-implementationgit 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/spec-driven-implementation)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/spec-driven-implementation"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/spec-driven-implementation/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/spec-driven-implementation"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/spec-driven-implementation.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 | $0.00043 | $0.00728 |
| Opus 5.5 | $0.00017 | $0.00291 |
| Sonnet 5.5 | $0.00009 | $0.00146 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
spec-driven-implementation 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec driven implementation
Contract
| Field | Bound contract |
|---|---|
| Trigger | Starting a significant feature or when specs are checked in. |
| Authority | Reversible local: writes only checked-in spec files and implementation; rollback is version control (if commit is not yet pushed). No remote mutation. |
| Side effect | Creates or updates checked-in spec files within the project. |
| Done | Specs exist, are behavioral, and stay current with what ships. |
Inputs
- Feature brief (required): natural-language description of the feature to implement.
- Existing specs (optional): any spec files already present in the project. If absent, the skill treats the feature as greenfield.
- Scope anchor (required): the module, package, or directory boundary the feature affects.
Refusal
- Spec drift: implementation adds behavior not covered by any spec. Remove the undocumented behavior or add a covering spec before proceeding.
- Scope overrun: the feature brief names more surface than the scope anchor. Stop and report the overrun; do not widen scope without explicit human confirmation.
- Non-behavioral spec: a proposed spec line describes a solution rather than behavior. Reject it; replace with an observable criterion.
- Unreachable rollback: VCS commit already pushed. Authority is exhausted; surface the conflict and stop. Do not overwrite remote history.
Procedure
- Bound the scope. From the feature brief and scope anchor, enumerate every file that will be created or modified. If the scope is ambiguous, stop and state the ambiguity rather than inferring a larger surface. Done when: the file set is enumerated or ambiguity is reported.
- Audit existing specs. For each spec file already present in the affected scope, verify it is behavioral: each statement describes observable behavior or acceptance criteria, not implementation design. Discard or narrow any spec line that prescribes a solution path. Done when: every existing spec is verified behavioral.
- Identify spec gaps. Map every feature-brief item to at least one behavioral statement. Mark any item that cannot be expressed as observable behavior as out of scope. Done when: every brief item maps to a behavioral statement or is marked out of scope.
- Write or update spec files. For each gap, add a new spec section with a unique label, the behavioral statement, any preconditions and expected outcomes, and the pass/fail criterion that a test could verify. Place each spec in the file that most directly covers the affected surface. Done when: every gap has a spec section.
- Verify spec-implementation alignment. Confirm that no spec file contradicts an existing implementation. If a conflict exists, surface it before writing. Done when: no spec contradicts existing implementation.
- Write or confirm the implementation. Implement the feature to satisfy the spec. Do not add behavior not described by a spec. Done when: the implementation satisfies every spec.
- Commit with a spec-referencing message. VCS-commit the spec and implementation files with a message that names the spec label(s) satisfied. Done when: one commit names the satisfied spec labels.
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 Changed · -9 tokens per session 4c1041378010
- 1mo ago First seen · 43 lines · 52 tokens per session scan A 1fb5ca39fa90
spec-driven-implementation is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (37 stars, last pushed 21d ago), licensed Apache-2.0. It adds 43 tokens to every session and 728 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…