fastopt-extreme

fastopt-extreme is a skill for Codex from OutlineDriven/outline-driven-development. It costs 52 tokens per session (754 once invoked), scanned A, original, Apache-2.0.

A read-only workflow for estimating which code paths are likely hot and examining cold paths where simplification may help without adding unnecessary complexity.

In plain words
What is it for?
It is for analyzing a named code region, estimating likely hot paths from usage and code structure, and producing benchmark designs for both hot and cold paths.
Why use it?
It encourages performance ideas to remain testable hypotheses and avoids complicated changes that have no measured justification.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit It is for analyzing a named code region, estimating likely hot paths from usage and code structure, and producing benchmark designs for both hot and cold paths.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/outlinedriven/outline-driven-development/fastopt-extreme
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.

Any agent
npx skills add OutlineDriven/outline-driven-development --skill fastopt-extreme
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/outline-driven-development

Made for: Codex.

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-extreme

README.md
[![agentmods](https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/fastopt-extreme/github.svg)](https://agentmods.dev/skills/outlinedriven/outline-driven-development/fastopt-extreme)
Your own site
<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/fastopt-extreme"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/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.

agentmods 80×15 button for fastopt-extreme

Your own site · 80×15
<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/fastopt-extreme"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/fastopt-extreme.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 754 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00052 $0.00754
Opus 5 $0.00026 $0.00377
Sonnet 5 $0.00010 $0.00151
Haiku 4.5 $0.00005 $0.00075

Measured 5d ago against content hash 6a9b390a928a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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 5d 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

Copies of this mod

1 near-identical copy found in the catalogue:

.devin/skills/fastopt-extreme/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 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 and complexity-neutral cold paths.
Done Hot and cold path hypotheses and benchmark designs 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

  1. 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.
  2. 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.
  3. 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.
  4. 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.
  5. 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.
  6. 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.
  7. 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.

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. 5d ago First seen · 40 lines · 52 tokens per session scan A 6a9b390a928a

Subscribe to this mod's changes

fastopt-extreme is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 52 tokens to every session and 754 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 2026-09-03.