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 skill-gap-findergit 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/skill-gap-finder)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/skill-gap-finder"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/skill-gap-finder/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/skill-gap-finder"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/skill-gap-finder.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 | $0.00040 | $0.00640 |
| Opus 5 | $0.00020 | $0.00320 |
| Sonnet 5 | $0.00008 | $0.00128 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
skill-gap-finder 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 3d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill gap finder
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user suspects no installed skill covers a task, or wants exhaustive proof that a task is a skill gap before requesting a new skill. |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. Consults the installed skill catalog; never invokes or routes to the matched skill. |
| Side effect | None. Catalog lookup only; no persistent writes. |
| Done | Either an owning skill is named with its trigger sentence (without invocation), or a missing-skill brief is produced proving no installed skill covers the task. |
Inputs
- The task description or user request that needs gap analysis.
- The installed skill catalog, available at runtime through the host harness.
Both are required. If the catalog is unavailable, stop and report the blocker.
Procedure
- Extract the core action and domain from the task description. Done when: the core action and domain are identified.
- Search the installed skill catalog exhaustively for skills whose trigger predicate could match the extracted action and domain. Test broad and narrow phrasings of the task to avoid false gaps. Done when: the matching set is enumerated with the search strategy recorded.
- If one or more skills match, name the best-matching skill and quote its trigger sentence. Report the selection rationale. Do not invoke the skill or route the user to it: naming the owner is the terminal output. Done when: the owning skill is named with its trigger sentence and rationale, without invocation.
- If no skill matches, produce a missing-skill brief containing: the task description, the exhaustive search strategy used and why it found no match, and the trigger predicate a new skill would need. Done when: the brief contains all three elements.
- Never invent behavior, fork a near-duplicate, or widen scope. Done when: no invention, fork, or scope widening occurred.
Failure and recovery
| Failure class | Rule |
|---|---|
| Ambiguous task | Stop. Ask the user to clarify the task before searching. |
| Catalog unavailable | Stop. Report that the catalog could not be read. Do not guess. |
| Multiple equal matches | Name all matching skills with their trigger sentences. Do not pick one. Report the overlap and let the user decide. |
| Near-duplicate detected | Produce a missing-skill brief instead of forking. Record the overlap. |
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.
- 3d ago Changed · -18 tokens per session 322e3916fc3a
- 5d ago First seen · 44 lines · 58 tokens per session scan A 04dd6227e2bb
skill-gap-finder is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 640 once invoked, about $0.0002 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…