agentmods.dev

runx

runx is a skill for Claude Code from bittencourtthulio/expxdev. It costs 71 tokens per session (4,514 once invoked), scanned A, original, MIT.

Use ao relatar defeito em sistema que já existe: não funciona como deveria, não segue o padrão esperado, trava, some ou dá valor errado — mesmo sem a palavra bug. Inclui falha de interface e interação (arrastar, clicar, salvar) e ajuste de tela, cálculo ou campo. Feature nova é sprintx.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 .claude/runx-hooks/comum/doctor.py.

not rated 3repo 1mo ago A scan 71 tokens original MIT
Compare 6 skills from other repositories ↓
View source ↗ bittencourtthulio/expxdev npmjs.com
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/bittencourtthulio/expxdev
agentmods
npx agentmods add skills/bittencourtthulio/expxdev/runx

Made for: Claude Code.

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 runx

README.md
[![agentmods](https://agentmods.dev/badge/skills/bittencourtthulio/expxdev/runx/github.svg)](https://agentmods.dev/skills/bittencourtthulio/expxdev/runx)
Your own site
<a href="https://agentmods.dev/skills/bittencourtthulio/expxdev/runx"><img src="https://agentmods.dev/badge/skills/bittencourtthulio/expxdev/runx/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 runx

Your own site · 80×15
<a href="https://agentmods.dev/skills/bittencourtthulio/expxdev/runx"><img src="https://agentmods.dev/badge/skills/bittencourtthulio/expxdev/runx.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,514 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.
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 $0.00071 $0.04514
Opus 5.5 $0.00028 $0.01806
Sonnet 5.5 $0.00014 $0.00903
Haiku 4.5 $0.00007 $0.00451

Measured today against content hash e1030339eb23, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

runx 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 today.

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.

.claude/skills/runx/SKILL.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

runx

runx é a metade Run do método da Expx (Exponencial): a sustentação do dia a dia. A metade Build é a sprintx, que planeja features novas do zero. As duas compartilham a mesma disciplina de engenharia — base antes do plano, hierarquia sprint → fase → task, TDD obrigatório, critério de aceite verificável, paralelismo declarado, execução guiada por orquestrador. Muda o gatilho e o tamanho, nunca o rigor.

Princípio central

Não se corrige o que não se entendeu, e não se planeja o que não se mapeou. Primeiro a base do que será tocado, depois a causa, depois o plano, depois o código. O escopo fica travado no que a investigação provou: o que não está lá não é tocado.

Fronteira de escopo

runx começa quando o chamado já chegou na mão do desenvolvedor. O que vem antes — cliente reclama, suporte atende e cadastra a ocorrência — acontece fora daqui e chega pronto.

runx termina quando os relatórios estão gravados e a ocorrência está encerrada. O deploy em si é externo: runx registra que foi liberado, não executa o deploy.

Tipos de ocorrência

Tipo Significado
bug defeito em comportamento existente
melhoria-ui mudança visual, layout, componente
melhoria-ux mudança de fluxo, navegação, usabilidade
novo-relatorio relatório novo dentro de estrutura existente
regra-de-calculo alteração de fórmula ou regra de negócio
campo-novo novo campo em tela, formulário ou entidade
outro qualquer coisa que não caiba acima

O tipo é determinado no início e governa o comportamento do estágio E1: bug exige causa raiz comprovada; os demais tipos entram em análise de impacto.

Contratos

Contrato da Task — toda task declara, obrigatoriamente

Campo Conteúdo
id T-NN.MM
titulo título curto
objetivo uma frase
arquivos criados e alterados
teste_regressao apenas na primeira task da primeira fase: o teste que reproduz o problema e hoje falha. Obrigatório quando tipo: bug
teste_integracao o que valida, contra o quê
teste_funcional o que valida, com qual entrada e saída
criterio_aceite verificável, binário, sem adjetivo
depende_de [ids] ou []
paralelizavel true | false
status pendente | em_andamento | concluida | bloqueada

Read the full file on GitHub · 257 lines

Files

What ships with it

22 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. today First seen · 257 lines · 71 tokens per session scan A e1030339eb23

Subscribe to this mod's changes

runx is a skill published in the GitHub repository bittencourtthulio/expxdev (3 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 4,514 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-07.

Claude CodeDebuggingProject managementagent-skillscliexpxopencoderunx
Related

runx compared with skills from other repositories

runx next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
runxbittencourtthulio/expxdevSkill31mo agoMITA71Claude Code
ph-debugjyt6640/persona-harnessSkill2329d agoApache-2.0A25Claude Code, Codex
ph-lsp-setupjyt6640/persona-harnessSkill2329d agoApache-2.0A22Claude Code, Codex
bug-investigation1024XEngineer/bytemindSkill273mo agoMITA16Claude Code
code_explorergoogle-gemini/gemini-cliSkill109kyesterdayApache-2.0A28Gemini CLI
test-failure-explorerQwenLM/qwen-codeSkill29kyesterdayApache-2.0A32Claude Code, Codex
session-investigatorevalstate/fast-agentSkill4.0kyesterdayApache-2.0A68Claude Code, Codex