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-doctorgit 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-doctor)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/skill-doctor"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/skill-doctor/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-doctor"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/skill-doctor.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 | $0.00038 | $0.01794 |
| Opus 5 | $0.00019 | $0.00897 |
| Sonnet 5 | $0.00008 | $0.00359 |
| Haiku 4.5 | $0.00004 | $0.00179 |
Grade A, and why
skill-doctor 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 4d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill doctor
Contract
| Field | Bound contract |
|---|---|
| Trigger | User wants agent setup graded from conversation history. |
| Authority | Reversible local: writes only to a scratch report directory under the current working tree; rollback is deleting that directory. No remote mutation. |
| Side effect | Creates one scratch report directory containing report.html and supporting assets. Never modifies real skill files, configuration, or conversation history. |
| Done | report.html exists in the scratch directory and renders a normalized 0-10 efficiency score, a normalized 0-10 code quality score (or N/A when the session has no code changes), per-turn findings with evidence citations (or no findings when every scored sub-score is at maximum), and ranked improvement suggestions (or none when every scored sub-score is at maximum). |
Inputs
- Conversation history: a session transcript from the current agent harness. Accept one of:
- A file path to a transcript log (JSON, JSONL, or plain-text log).
- A directory of transcript files; process the most recent file.
- If neither is supplied, attempt to locate the most recent session transcript in the default harness log directory.
- Output directory (optional): path for the scratch report directory. Default:
./skill-doctor-report-<timestamp>.
Procedure
-
Collect session data.
- Locate the conversation history from the supplied path, directory, or default harness log.
- If no transcript is found, write a minimal report.html stating "No conversation history found" and stop.
- Read the transcript file. If the file is empty or contains fewer than 2 turns, write a minimal report.html stating "Session too short to assess" and stop. Done when: the transcript is located and read, or a minimal report is written for the empty/short case.
-
Decode transcript into structured turns.
- Parse each message into a turn record with fields:
role(user/assistant/tool),content(text),tool_name(if applicable),tool_input(if applicable),tool_output(if applicable),timestamp(if available). - For JSON/JSONL transcripts, parse each line or object directly.
- For plain-text logs, identify turn boundaries by role markers (e.g., "User:", "Assistant:", "Tool:", or harness-specific prefixes). Extract tool calls from fenced code blocks or structured markers.
- Produce an ordered list of turn records. Done when: an ordered list of turn records is produced.
- Parse each message into a turn record with fields:
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.
- 4d ago Changed · -20 tokens per session 7a70d0b040d8
- 6d ago First seen · 105 lines · 58 tokens per session scan A c3a4c8961432
skill-doctor is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 38 tokens to every session and 1,794 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…