fastopt

fastopt is a skill for Claude Code, Codex from OutlineDriven/odin-claude-plugin. It costs 49 tokens per session (702 once invoked), scanned A, a copy of fastopt, Apache-2.0.

A read-only performance-planning tool for suspected hot paths, meaning code sections expected to consume much of the runtime.

In plain words
What is it for?
It helps inspect named functions or call sites, record plausible sources of cost, and design benchmarks for the workload that makes each path busy.
Why use it?
It separates unmeasured performance guesses from proven slowdowns and prevents speed claims before benchmarks exist.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

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/fastopt
Any agent
npx skills add OutlineDriven/odin-claude-plugin --skill fastopt
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 fastopt

README.md
[![agentmods](https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/fastopt.svg)](https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/fastopt)
Your own site
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/fastopt"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/fastopt.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 702 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00049 $0.00702
Opus 5 $0.00024 $0.00351
Sonnet 5 $0.00010 $0.00140
Haiku 4.5 $0.00005 $0.00070

Measured 2d ago against content hash d65364c19f3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

fastopt 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 2d 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.

Origin

This is a copy

100% identical to fastopt — 0 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.

plugins/odin-code-advanced/skills/fastopt/SKILL.md · 40 lines

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

Contract

Field Bound contract
Trigger User wants to optimize suspected hot paths without waiting for benchmarks, labeling claims as hypotheses.
Authority Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation.
Side effect Chat output only: hypotheses and benchmark designs before any mutation or performance claim.
Done Hypotheses and benchmark designs for suspected hot paths are emitted; no mutation or speed claim made.

Inputs

Required: one or more suspected hot paths named by the user (file, function, or call site) and the workload or input shape that makes each path hot.

Optional: prior measurements, profiling traces, or environment constraints the user supplies. Absent measurements are treated as unmeasured, not as evidence of slowness.

Procedure

  1. For each named hot path, read the source and surrounding call graph read-only; record the inputs, allocations, loops, and branches that plausibly dominate cost. Done when: every named path is read and its cost-plausible elements recorded.
  2. Label every cost observation a hypothesis, not a finding: state the assumed workload, the assumed dominant operation, and the assumed magnitude rank, with no speed claim. Done when: every observation carries its hypothesis label with workload, dominant operation, and magnitude rank.
  3. For each hypothesis, design a benchmark that would confirm or refute it: name the metric, the baseline, the variant, the workload generator, the warm-up, the repetition count, and the noise controls. Done when: every hypothesis has a benchmark design with all seven elements named.
  4. Bound the change scope implied by each hypothesis to the named path; do not propose edits outside it or assume a fix is correct. Done when: every hypothesis's implied change scope is bounded to its named path.
  5. If a hypothesis cannot be tested without mutating code, state the minimal mutation needed to measure it and stop before performing it. Done when: the blocking reason and minimal mutation are stated, or the hypothesis is testable read-only.
  6. Emit the hypotheses and benchmark designs as chat output. Make no mutation and no speed claim. Done when: the chat report is emitted with no mutation and no speed claim.

Read the full file on GitHub · 40 lines

Files

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.

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. 2d ago First seen · 40 lines · 49 tokens per session scan A d65364c19f3b

Subscribe to this mod's changes

fastopt is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 49 tokens to every session and 702 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, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

java-fix

Diagnoses and fixes Java compile errors, runtime exceptions, and stack traces. Use when user asks to "fix this error", "this won't compile", "I'm getting an exception", "debug this", or "build is failing".

ducpm2303/claude-java-plugins · 46 tokens

java-perf-check

Quick Java performance scan flagging N+1 queries, memory issues, threading problems, and algorithmic hotspots. Use when user asks to "check performance", "performance scan", "any N+1 queries", "performance issues", "is this efficient", or "slow code".

ducpm2303/claude-java-plugins · 56 tokens

postmortem

Auto-generates a structured postmortem from a completed campaign. Reads the campaign file, telemetry logs, and feature ledger. Produces a documented analysis of what broke, what the safety systems caught, and what patterns emerged. Can also be invoked manually for any incident.

SethGammon/Citadel · 58 tokens

health-check

Runs plugin health checks (venv packages, skill registration, and album slug collisions). Use when the user asks to check plugin health, verify setup, or troubleshoot missing skills.

bitwize-music-studio/claude-ai-music-skills · 38 tokens

cloudflare-workers-observability

Cloudflare Workers observability with logging, Analytics Engine, Tail Workers, metrics, and alerting. Use for monitoring, debugging, tracing, or encountering log parsing, metric aggregation, alert configuration errors.

secondsky/claude-skills · 47 tokens

cloudflare-workers-performance

Cloudflare Workers performance optimization with CPU, memory, caching, bundle size. Use for slow workers, high latency, cold starts, or encountering CPU limits, memory issues, timeout errors.

secondsky/claude-skills · 42 tokens