focused-fix

focused-fix is a command for Claude Code from ricneves-ai/flowgrammers-skills. It costs 43 tokens per session (996 once invoked), scanned A, original, MIT.

A structured repair process for fixing an entire software feature or module, including its files and dependencies. It maps the feature’s scope, inputs, outputs, and connections before checking and repairing it.

In plain words
What is it for?
Use it when a feature or module needs a systematic investigation across its files, imports, environment settings, database models, APIs, and users.
Why use it?
It reduces the risk of fixing one file while leaving related code, configuration, APIs, or consumers broken. The process makes the repair boundary and missing dependencies visible.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it when a feature or module needs a systematic investigation across its files, imports, environment settings, database models, APIs, and users.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ricneves-ai/flowgrammers-skills/focused-fix
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.

Clone the repo
git clone --depth 1 https://github.com/ricneves-ai/flowgrammers-skills

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 focused-fix

README.md
[![agentmods](https://agentmods.dev/badge/commands/ricneves-ai/flowgrammers-skills/focused-fix/github.svg)](https://agentmods.dev/commands/ricneves-ai/flowgrammers-skills/focused-fix)
Your own site
<a href="https://agentmods.dev/commands/ricneves-ai/flowgrammers-skills/focused-fix"><img src="https://agentmods.dev/badge/commands/ricneves-ai/flowgrammers-skills/focused-fix/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 focused-fix

Your own site · 80×15
<a href="https://agentmods.dev/commands/ricneves-ai/flowgrammers-skills/focused-fix"><img src="https://agentmods.dev/badge/commands/ricneves-ai/flowgrammers-skills/focused-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 996 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 $0.00043 $0.00996
Opus 5 $0.00022 $0.00498
Sonnet 5 $0.00009 $0.00199
Haiku 4.5 $0.00004 $0.00100

Measured 8d ago against content hash c68504a84148, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

focused-fix 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 8d 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.

commands/focused-fix.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/focused-fix

Repara sistematicamente uma feature ou módulo inteiro usando o protocolo de 5 fases. Alvo: $ARGUMENTS (caminho de feature ou nome de módulo).

Se $ARGUMENTS estiver vazio, pergunte ao usuário qual feature/módulo corrigir.

Protocolo — Execute TODAS as 5 Fases EM ORDEM

Fase 1: ESCOPO — Mapeie o Limite da Feature

  1. Identifique a pasta/arquivos principais da feature alvo
  2. Leia TODOS os arquivos dessa pasta — entenda seu propósito
  3. Crie um manifesto da feature:
ESCOPO DA FEATURE:
  Caminho principal: <caminho>
  Pontos de entrada: [arquivos importados por outras partes do app]
  Arquivos internos: [arquivos usados apenas dentro desta feature]
  Total de arquivos: N

Fase 2: RASTREAMENTO — Mapeie Todas as Dependências

ENTRADA (o que esta feature importa):

  • Para cada instrução de importação, rastreie até a origem, verifique se existe e está exportada
  • Verifique variáveis de ambiente, arquivos de config, modelos de DB, endpoints de API, pacotes de terceiros

SAÍDA (o que importa desta feature):

  • Pesquise todo o codebase por importações desta feature
  • Verifique se os consumidores usam a API/interface correta

Produza um mapa de dependências com entradas, saídas, variáveis de ambiente e arquivos de configuração.

Fase 3: DIAGNÓSTICO — Encontre Todos os Problemas

Execute TODAS as verificações de diagnóstico:

  • Código: importações resolvidas, sem dependências circulares, tipos consistentes, tratamento de erros, TODO/FIXME
  • Runtime: variáveis de ambiente definidas, migrations atualizadas, shapes de API corretos
  • Testes: execute TODOS os testes relacionados, registre falhas, verifique cobertura
  • Logs: verifique git log para alterações recentes, pesquise logs de erro
  • Config: valide arquivos de config, verifique divergências entre dev e prod

Para cada problema encontrado:

  • Confirme a causa raiz com evidências antes de adicionar à lista de correções
  • Atribua risco: ALTO (API pública, auth, >3 consumidores) / MÉDIO (interno com testes) / BAIXO (módulo folha)

Read the full file on GitHub · 92 lines

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. 8d ago First seen · 92 lines · 0 tokens per session scan A c68504a84148

Subscribe to this mod's changes

focused-fix is a command published in the GitHub repository ricneves-ai/flowgrammers-skills (112 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 996 once invoked, about $0.0002 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.