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 fastopt-extremegit 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/fastopt-extreme)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/fastopt-extreme"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/fastopt-extreme/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/fastopt-extreme"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/fastopt-extreme.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00041 | $0.00751 |
| Opus 5 | $0.00020 | $0.00376 |
| Sonnet 5 | $0.00008 | $0.00150 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
fastopt-extreme 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.
This is a copy
100% identical to fastopt-extreme — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fastopt extreme
Contract
| Field | Bound contract |
|---|---|
| Trigger | User wants to optimize estimated hot paths and complexity-neutral cold paths while refusing complexity theater. |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | Chat output only: hypotheses and benchmark designs for estimated hot paths; simplification proposals for complexity-neutral cold paths. |
| Done | Hot-path hypotheses with benchmark designs and cold-path simplification proposals are emitted; complexity theater is refused. |
Inputs
The target code region or module to analyze. Optional: known call frequencies, profiling data, or prior benchmark results that sharpen hot-path estimates. If no code is supplied, request it before proceeding.
Procedure
- Bound scope to the named code region or module. Do not widen to unrelated code. Done when: the scope is bounded to the named region or module.
- Estimate hot paths from call frequency, loop depth, allocation density, and I/O or syscall blocking. Label every estimate as a hypothesis, not a measured fact. Done when: every hot-path estimate is labeled as a hypothesis with its basis stated.
- Identify complexity-neutral cold paths: paths whose optimization adds no new abstraction, wrapper, configuration flag, caching layer, or indirection. The change must be simpler than or equal in complexity to the original. Done when: every cold-path candidate is classified as complexity-neutral or rejected.
- For each hot-path hypothesis, design a benchmark that would confirm or refute it. State the metric, the baseline measurement, and the falsification condition under which the hypothesis is rejected. Done when: every hot-path hypothesis has a benchmark design with metric, baseline, and falsification condition.
- For each complexity-neutral cold-path candidate, state the specific simplification and why it adds no complexity. Done when: every cold-path candidate has its simplification and complexity justification stated.
- Refuse complexity theater: reject any proposed optimization that introduces a new abstraction, wrapper, flag, caching layer, or indirection whose complexity exceeds the gain it claims. State the refusal, the complexity cost, and the claimed gain. Done when: every complexity-theater proposal is refused with its cost and claimed gain stated.
- Emit all hypotheses, benchmark designs, simplification proposals, and refusals as chat output. Do not mutate any file. Done when: the chat report is emitted with no file mutation.
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 · -11 tokens per session 8f260ede3dc0
- 5d ago First seen · 40 lines · 52 tokens per session scan A 6a9b390a928a
fastopt-extreme is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed 2d ago), licensed Apache-2.0. It adds 41 tokens to every session and 751 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to fastopt-extreme, differing in 6 lines, and is treated as a copy.
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…