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 source-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/source-driven)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/source-driven"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/source-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/source-driven"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/source-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 | $0.00036 | $0.00831 |
| Opus 5.5 | $0.00014 | $0.00332 |
| Sonnet 5.5 | $0.00007 | $0.00166 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
source-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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Source-driven development
Contract
| Field | Bound contract |
|---|---|
| Trigger | The current task is writing or verifying framework-specific code, boilerplate, or a documented, correct implementation. |
| Authority | Reversible local: writes only framework-specific code plus full-URL citations; rollback is version control (revert to last commit on failure). No remote mutation. |
| Side effect | Local writes with explicit UNVERIFIED flags for unverifiable patterns. |
| Done | Every framework-specific decision is backed by a cited official source and unverified patterns are explicitly flagged. |
Inputs
- Framework context (required): the framework, language, or library.
- Dependency file (required):
package.json,requirements.txt,go.mod,Cargo.toml,Gemfile,composer.json, orpyproject.toml. - Stack examples (optional): examples supplied by the caller. This skill has no bundled stack-reference dependency.
Procedure
- Read the project's dependency file and state the exact pinned versions. Done when: every dependency in the file has its pinned version stated.
- For each dependency about to be written against, read the latest stable release from the release channel (registry, releases page, official download page). Report pinned and latest versions side by side. Name the gap when they differ. Done when: each touched dependency shows pinned and latest side by side, with the gap named when they differ.
- Fetch the official documentation page for the exact feature being implemented. Use the source hierarchy: (1) official docs, (2) official blog/changelog, (3) web standards references (MDN, web.dev), (4) runtime compatibility references. Never use Stack Overflow, blog posts, tutorials, or training data as primary sources. Done when: the fetched page for each feature comes from the highest available tier of the hierarchy and no banned source is cited.
- Extract the implementation patterns shown in the fetched docs. Use those exact API signatures. If the docs show a newer approach, use the newest one the pinned version supports. Do not use deprecated forms. Done when: every written API signature matches the fetched docs for the pinned version and no deprecated form remains.
- When official sources contradict each other, report the discrepancy. Do not silently choose one. Done when: each contradiction surfaces as a CONFLICT DETECTED report rather than a silent pick.
- Write code that follows the documented patterns. Every non-obvious decision gets a full-URL citation in a code comment. Quote the relevant passage when it supports a non-obvious decision. Done when: each non-obvious decision carries a full-URL citation, quoting the supporting passage where one exists.
- Flag any pattern that could not be verified against official documentation with an explicit UNVERIFIED marker rather than a hedged disclaimer or confident guess. Done when: every unverified pattern carries an UNVERIFIED marker and none is presented as confirmed.
What ships with it
2 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 · -16 tokens per session 20a81a6df32f
- 1mo ago First seen · 42 lines · 52 tokens per session scan A 0cf9bdb42e2a
source-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 36 tokens to every session and 831 once invoked, about $0.0001 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…