model-selector

model-selector is a skill for Claude Code, Codex from JotJunior/cstk. It costs 97 tokens per session (2,463 once invoked), scanned A, original, MIT.

A rule-based guide that classifies a text task as shallow, medium, or deep and suggests an abstract model label such as haiku, sonnet, opus, or current model.

In plain words
What is it for?
Use it to assess the complexity of a text-based task; it does not switch models, check prices, or handle non-text input.
Why use it?
It gives an offline, repeatable model recommendation before an expensive skill or subagent is used, while leaving the final choice to the operator.

Skill for Claude CodeCodex

Part of the cstk plugin — 21 skills, 7 commands, 7 agents 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/jotjunior/cstk/model-selector
Any agent
npx skills add JotJunior/cstk --skill model-selector
Clone the repo
git clone --depth 1 https://github.com/JotJunior/cstk

Made for: Claude Code, Codex.

Or install cstk, the plugin that ships this one along with the rest of its 21 skills, 7 commands, 7 agents.

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 model-selector

README.md
[![agentmods](https://agentmods.dev/badge/skills/jotjunior/cstk/model-selector.svg)](https://agentmods.dev/skills/jotjunior/cstk/model-selector)
Your own site
<a href="https://agentmods.dev/skills/jotjunior/cstk/model-selector"><img src="https://agentmods.dev/badge/skills/jotjunior/cstk/model-selector.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,463 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 $0.00097 $0.02463
Opus 5 $0.00048 $0.01231
Sonnet 5 $0.00019 $0.00493
Haiku 4.5 $0.00010 $0.00246

Measured 4d ago against content hash 98c9a4a2ed80, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

model-selector 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 4d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/classify.sh, scripts/report.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/cstk/skills/model-selector/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Model Selector

Classifica uma tarefa proxima em faixa de complexidade (rasa | media | profunda) com base em catalogo deterministico de sinais e sugere um rotulo abstrato de modelo (haiku | sonnet | opus | manter-atual)

  • score 0..2 + alternativa de fallback. Decisao final permanece do operador/orquestrador — a skill nunca troca modelo silenciosamente.

A skill e POSIX-pura (sem jq, sem bash-isms no caminho de classificacao) e roda offline — zero coleta remota (Principio IV).

Quando usar

Use quando o orquestrador (agente-00c, feature-00c) ou operador humano quiser uma sugestao deterministica de qual modelo Claude rodar a proxima tarefa, baseada em sinais textuais (verbos, ferramentas) no input.

NAO use quando:

  • O input nao e texto (binario, imagem, audio) — skill e text-only.
  • A decisao precisa de contexto externo (precos correntes, modelo ativo no harness, billing API) — skill nao consulta estado externo.
  • Voce quer troca AUTOMATICA de modelo — esta skill apenas SUGERE. Quem troca e o operador ou o orquestrador apos registrar Decisao.

Contrato I/O (resumo)

Lado Forma
Input UMA string textual, 0..4096 chars, sem null-byte
Output sucesso Markdown em stdout com 4 secoes fixas: ## Sugestao, ## Sinais detectados, ## Justificativa, ## Acao sugerida
Exit 0 sucesso, 2 uso incorreto, 1 erro interno (catalogo ausente/invalido)

Contrato completo (campos obrigatorios, invariantes testaveis, edge cases): contracts/skill-io.md.

Exemplo minimo de output:

## Sugestao

**modelo**: haiku
**score**: 2
**alternativa**: sonnet

## Sinais detectados

- rode: rasa (peso=1)
- grep: rasa (peso=1)

## Justificativa

Verbos deterministicos (`rode`) + ferramenta POSIX (`grep`) indicam
operacao mecanica. Faixa rasa vence com 2 sinais.

## Acao sugerida (operador humano)

`/model haiku` (se operador quiser trocar; nao executado pela skill)

Read the full file on GitHub · 196 lines

Files

What ships with it

10 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. 4d ago First seen · 196 lines · 97 tokens per session scan A 98c9a4a2ed80

Subscribe to this mod's changes

model-selector is a skill published in the GitHub repository JotJunior/cstk (23 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 2,463 once invoked, about $0.0005 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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