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 extremely-optimizegit 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/extremely-optimize)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/extremely-optimize"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/extremely-optimize/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/extremely-optimize"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/extremely-optimize.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 | $0.00030 | $0.01685 |
| Opus 5.5 | $0.00012 | $0.00674 |
| Sonnet 5.5 | $0.00006 | $0.00337 |
| Haiku 4.5 | $0.00003 | $0.00169 |
Grade A, and why
extremely-optimize 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extremely optimize
Contract
| Field | Bound contract |
|---|---|
| Trigger | Subsystem or repo-wide performance campaign against a measured floor; the user says "make this as fast as possible", "extremely optimize", or "grill every inefficiency" |
| Authority | Reversible local: writes only VCS-tracked source targets (destructive; the exact set shown before mutation); rollback is version control. No remote mutation. |
| Side effect | Hot-path source targets rewritten as atomic commits; non-wins reverted; boundary surfaces gated before any touch |
| Done | Hot units rebuilt with an even win, cold units graded fixed/at-floor/left, residue gone, verifier green, target landed atomically |
Inputs
- A named subsystem path, or no path for a repo-wide survey. Repo-wide work is opt-in and never inferred. A bare invocation profiles the repo's own workload, then works the ranked list.
- One runnable workload command exercising the target with representative input and taking at least one second of wall clock. Must be supplied or constructed before measurement begins.
- The repo's own verifier command. Must be supplied or discovered before any target lands.
Procedure
-
Pin the workload and baseline. Run
hyperfine --warmup 3 --min-runs 10 '<cmd>'. Record median, stddev, min, max. Reject the measurement while stddev exceeds 20 % of median: pin CPU frequency, isolate the process, widen--min-runs, or enlarge the input until the noise clears. Use this number for every later comparison. Done when: a stable baseline median is recorded with stddev under 20 % of median. -
Split hot from cold. Profile the workload. A unit is hot when it holds ≥ 5 % of total measured time or its call count scales with input size; everything else is cold. Write both lists down. Where a sampling profiler disagrees with a call-count argument, believe the call count and confirm by instrumentation. Done when: both hot and cold lists are written down.
-
State the contract, compute the floor. Work the hot list in descending order of time share. For each unit, write what it owes its callers based on call sites, tests, and the signature: never its own internals. Compute the floor from that contract alone: bytes that must move at achievable bandwidth, the algorithmic lower bound at a measured per-operation cost, and syscalls or round-trips the protocol cannot avoid. Show the arithmetic with
eval, never in prose. Divide measured cost by floor; that multiple is the unit's headroom. A unit already within 2× of its floor is finished: record it and move on. Done when: every hot unit has its contract stated, floor computed, and headroom multiple recorded; units within 2× of floor are marked finished.
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 · -24 tokens per session d6e5ff035d62
- 1mo ago Changed · -62 lines · -34 tokens per session 440ec48f8779
- 1mo ago First seen · 121 lines · 88 tokens per session scan A 83ea73c4b238
extremely-optimize is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (37 stars, last pushed 21d ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,685 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 2026-08-30.
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…