reversa-optimize

reversa-optimize is a skill for Claude Code, Codex from sandeco/reversa. It costs 52 tokens per session (1,289 once invoked), scanned A, original, MIT.

A performance-refactoring guide for reducing a program’s running time, memory use, or resource consumption while keeping its output unchanged.

In plain words
What is it for?
Use it to measure a suspected bottleneck, record the improvement with numbers, and apply a controlled code change after safety and equivalence checks.
Why use it?
It prevents guesses from being treated as optimizations by requiring measurements before and after the change. It also separates performance work from simplifying code for readability.

Skill for Claude CodeCodex

About the project

Reversa is a reverse-engineering framework that analyzes legacy software and turns its hidden business rules, code flows, and architectural decisions into executable specifications for AI coding agents. Teams use it to help agents safely understand and change systems that lack reliable documentation. The catalogue skills provide the specialized agent workflows used to perform this analysis.

sandeco/reversa · 1,558 stars · on GitHub

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/sandeco/reversa/reversa-optimize
Any agent
npx skills add sandeco/reversa --skill reversa-optimize
Clone the repo
git clone --depth 1 https://github.com/sandeco/reversa

Made for: Claude Code, 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 reversa-optimize

README.md
[![agentmods](https://agentmods.dev/badge/skills/sandeco/reversa/reversa-optimize.svg)](https://agentmods.dev/skills/sandeco/reversa/reversa-optimize)
Your own site
<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-optimize"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-optimize.svg" alt="Measured on agentmods" 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 1,289 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 $0.00052 $0.01289
Opus 5 $0.00026 $0.00645
Sonnet 5 $0.00010 $0.00258
Haiku 4.5 $0.00005 $0.00129

Measured yesterday against content hash 7beac2168d0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reversa-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.

agents/reversa-optimize/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Você é o otimizador. Sua missão é reduzir tempo de execução, uso de memória ou consumo de recursos, sem alterar a saída para o mesmo conjunto de entradas, e sempre com número que comprove o ganho. Sem medição, é hipótese, não otimização.

Antes de começar

  1. Leia .reversa/state.json (output_folder, chat_language, doc_language, user_name)
  2. Leia _reversa_refactor/README.md (control_mode, safety_net_policy). Se _reversa_refactor/ não existir, aborte: "Rode /reversa-refactor primeiro."
  3. Converse em chat_language; escreva artefatos em doc_language; nunca use travessão

Seleção da oportunidade

  1. Com argumento (/reversa-optimize OPP-...): resolva no opportunities/ do contexto
  2. Sem argumento: aceite um alvo natural, resolva o contexto, crie a oportunidade optimize se preciso
  3. Se o alvo real é reduzir complexidade da lógica (não custo de recurso), reencaminhe a /reversa-simplify

Modo de controle

Siga o control_mode do README (gated por padrão): análise, medição e prova fluem; todo passo que toca o código passa por gate com diff.

Rede de segurança e equivalência (obrigatórias antes de tocar o código)

  1. Exija testes que fixem a saída do alvo; sem cobertura, ofereça testes de caracterização verdes antes de otimizar
  2. Equivalência de saída: comprove que a versão otimizada produz a mesma saída para o mesmo conjunto de entradas, incluindo edge cases (vazio, nulo, limites, concorrência)
  3. Recusada a rede, rebaixe para 🔴 e registre a ausência de prova

Medição (o coração deste agente)

  1. Declare a complexidade assintótica antes (tempo e espaço)
  2. Quando o harness puder executar o projeto, rode um benchmark real (mesma entrada, várias repetições) e registre o baseline. Quando não puder, use só a complexidade declarada e diga explicitamente que não houve benchmark de runtime (ver política de fallback do time)
  3. Otimização prematura ou micro-ganho que custa legibilidade sem retorno é rejeitado com justificativa

Read the full file on GitHub · 81 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. yesterday Changed · +10 lines 7beac2168d0a
  2. 5d ago First seen · 71 lines · 52 tokens per session scan A 6180039d158c

Subscribe to this mod's changes

reversa-optimize is a skill published in the GitHub repository sandeco/reversa (1,558 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 1,289 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens