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 review-speedreadgit 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/review-speedread)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/review-speedread"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/review-speedread/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/review-speedread"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/review-speedread.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 | $0.00064 | $0.00556 |
| Opus 5 | $0.00032 | $0.00278 |
| Sonnet 5 | $0.00013 | $0.00111 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
review-speedread 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 6d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review speedread
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user asks to see the change shape of a diff before reading the diff itself. |
| Authority | Read-only: no file mutation, no VCS write, no credential use, no remote or deployed resource touched. |
| Side effect | Chat output only: one compact visual or textual summary of the change shape. |
| Done | A change-shape summary is rendered in the chat and the human can proceed to read the diff. |
Inputs
Required: a diff context such as a PR/MR URL, a commit range, a branch comparison, or an explicit diff/path identifier. The human must supply or confirm the source; the skill does not search for it.
Procedure
- Detect the diff source. If the source is ambiguous, absent, or cannot be resolved, stop and report that no diff context is available.
- Retrieve the diff surface: file names, additions, deletions, and change type for each changed file. Stop rather than fetch full file contents.
- Render a compact change-shape summary as an ASCII table or structured paragraph. Include at minimum the changed-file count, total lines added and removed, and a short label for each changed file (e.g., "M src/foo.ts +12 -3", "A docs/readme.md +45 -0"). Highlight new and deleted files. Do not render the full diff.
- Present the summary in chat so the human can absorb the shape in one read before opening the diff.
Failure and recovery
- No-diff-context: the skill cannot locate the diff source. Returns "no diff context found"; does not fabricate a summary.
- Empty-diff: the diff exists but has no changes. Returns "diff is empty"; does not pretend a summary exists.
- Retrieval-failure: the diff cannot be fetched (network, auth, or permissions). Returns the failure message; does not retry or widen scope.
Partial-result rule: if retrieval succeeds for a subset of files, render what was retrieved and label it "partial" if the full set is not available.
Output
A chat-native change-shape summary: compact ASCII table or structured paragraph listing each changed file with its change type and line delta, plus aggregate totals. The human reads this and then reads the full diff.
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.
- 6d ago First seen · 37 lines · 64 tokens per session scan A 506378d8980f
review-speedread is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 64 tokens to every session and 556 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…