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 agentmods add skills/outlinedriven/odin-claude-plugin/extremely-optimizenpx 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.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.01705 |
| Opus 5 | $0.00027 | $0.00852 |
| Sonnet 5 | $0.00011 | $0.00341 |
| Haiku 4.5 | $0.00005 | $0.00170 |
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 yesterday.
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 | VCS-reversible destructive — changes restricted to VCS-tracked source targets, the exact set shown before mutation, version control used as recovery |
| 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.
- yesterday Changed · -62 lines · -34 tokens per session 440ec48f8779
- 5d 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 (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 1,705 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 2026-08-30.
Other skills, from other repositories
java-clean-arch
Reviews or implements Clean Architecture / Hexagonal Architecture (Ports & Adapters) and DDD tactical patterns for Java projects. Use when user asks to "apply clean architecture", "implement hexagonal architecture", "add ports and adapters", "apply DDD", "refactor to clean arch", "review architecture", or "add value…
java-adr
Creates, lists, and manages Architecture Decision Records for Java projects. Use when user asks to "create an ADR", "document this decision", "write an architecture decision", "add ADR", "list decisions", "show ADRs", or "record this architectural choice".
java-test
Generates JUnit 5 and Mockito unit tests or Testcontainers integration tests, auto-detecting project setup. Use when user asks to "write tests", "generate tests", "add unit tests", "create test class", "test this service", or "write integration tests".
java-jpa
Reviews Spring Data JPA for N+1 queries, fetch strategies, projections, and Specifications. Use when user asks to "review JPA", "check for N+1", "JPA performance", "review my entities", "check fetch strategy", or "review my repositories".
java-logging
Reviews Java logging for SLF4J best practices, MDC context, structured logging, and PII safety. Use when user asks to "review logging", "check my logs", "logging review", "is my logging correct", "MDC setup", or "check for PII in logs".
java-security
Reviews or implements Spring Security configuration — JWT authentication, OAuth2, method-level security, CORS, and CSRF. Use when user asks to "add authentication", "secure this API", "implement JWT", "configure Spring Security", "add OAuth2 login", "protect endpoints", or "review security config".