optimize

optimize is a skill for Claude Code, Codex from OutlineDriven/odin-claude-plugin. It costs 86 tokens per session (2,921 once invoked), scanned A, original, Apache-2.0.

A profiling and optimization process for making a selected code path faster or less wasteful. It measures candidate changes and keeps a fix only when the results support it.

In plain words
What is it for?
It profiles a target, tests possible hot-path changes, applies one verified improvement, and can add a CI check for an obvious bottleneck.
Why use it?
It replaces guesswork with benchmarks and protects against keeping an optimization that is smaller than measurement noise or fails to improve performance.

Skill for Claude CodeCodex

Part of the odin-code-advanced plugin — 50 skills shipped together

Install

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.

agentmods
npx agentmods add skills/outlinedriven/odin-claude-plugin/optimize
Any agent
npx skills add OutlineDriven/odin-claude-plugin --skill optimize
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/odin-claude-plugin

Made for: Claude Code, Codex.

Or install odin-code-advanced, the plugin that ships this one along with the rest of its 50 skills.

Wrote 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.

agentmods badge for optimize

README.md
[![agentmods](https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/optimize.svg)](https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/optimize)
Your own site
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/optimize"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/optimize.svg" alt="Measured on agentmods" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,921 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00086 $0.02921
Opus 5 $0.00043 $0.01460
Sonnet 5 $0.00017 $0.00584
Haiku 4.5 $0.00009 $0.00292

Measured yesterday against content hash ceed2a7f5efa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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.

plugins/odin-code-advanced/skills/optimize/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Optimize

Two modes share one authority: reversible local writes to the resolved target, never push, tag, publish, deploy, or mutate a remote. Full mode runs an isolated five-lens search with an integrated 1.05x gate and an atomic commit. Quick mode runs a single measure-identify-fix-verify loop with a noise-aware keep/revert and a CI guard for the obvious-bottleneck case.

Contract

Field Bound contract
Trigger The user asks to optimize code, make a path faster, reduce allocations, fix a performance regression, profile and optimize a path, symbol, or diff, or a performance requirement, slowness report, Core Web Vitals miss, or profiling evidence identifies a bottleneck.
Authority Reversibly modify only the resolved local target and .outline/optimize/<target>/ (full mode) or the named target (quick mode); commit one winning optimization (full mode) or apply one targeted fix (quick mode), but never push, tag, publish, deploy, or mutate a remote.
Side effect Full mode: append measurements and decisions to .outline/optimize/<target>/log.jsonl, benchmark isolated candidates, apply the winner, create one atomic commit. Quick mode: apply one targeted fix; may add a CI performance budget or field monitor.
Done Full mode: exit 0 only after the committed change preserves authorized behavior, passes the adversarial and repository gates, and measures at least 1.05x faster in the integrated benchmark. Quick mode: the identified bottleneck is measurably improved past noise, tests remain green, no new regressions, and a CI budget or field monitor guards the metric.

Inputs

Required (both modes): a resolvable path, symbol, diff, or active local change; a representative workload or benchmark command (full mode) or a performance symptom and the codebase under optimization (quick mode); and repository-native verification commands. A supplied profile or named hotspot is optional.

Optional (full mode): a performance budget, maximum gate attempts, maximum wall time, and minimum marginal speedup. An observable approximation is permitted only when the user's request already authorizes it and the exact changed contract is confirmed before mutation. If the target or workload cannot be resolved without guessing, stop with exit 11.

Read the full file on GitHub · 82 lines

Files

What ships with it

5 files 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.

Changes

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.

  1. yesterday First seen · 82 lines · 86 tokens per session scan A ceed2a7f5efa

Subscribe to this mod's changes

optimize is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), licensed Apache-2.0. It adds 86 tokens to every session and 2,921 once invoked, about $0.0004 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.

Related

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…

ducpm2303/claude-java-plugins · 68 tokens

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".

ducpm2303/claude-java-plugins · 54 tokens

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".

ducpm2303/claude-java-plugins · 57 tokens

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".

ducpm2303/claude-java-plugins · 60 tokens

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".

ducpm2303/claude-java-plugins · 63 tokens

java-health

Runs a holistic code health check scoring Security, Tests, Performance and Quality with A-F grades. Use when user asks to "check health", "score this project", "health check", "how good is this code", "overall assessment", or "code quality score".

ducpm2303/claude-java-plugins · 54 tokens