brain-linter

brain-linter is an agent for Claude Code from pwdev-solucoes/pwdev-claude-marketplace. It costs 102 tokens per session (802 once invoked), scanned A, original, Apache-2.0.

A wiki quality checker that compares an OKF knowledge wiki with a list of checking rules. It finds structural and content problems, then can apply approved automatic fixes.

In plain words
What is it for?
Use it to audit a wiki, produce a severity-ranked report, and apply only fixes that have been approved.
Why use it?
It removes the need to manually inspect every page for missing metadata, broken links, outdated information, misplaced files, and contradictions.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the pwdev-brain plugin — 1 skill, 5 commands, 2 agents shipped together

Good fit Use it to audit a wiki, produce a severity-ranked report, and apply only fixes that have been approved.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add pwdev-solucoes/pwdev-claude-marketplace
Claude Code
/plugin install pwdev-brain

Made for: Claude Code.

Or install pwdev-brain, the plugin that ships this one along with the rest of its 1 skill, 5 commands, 2 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 brain-linter

README.md
[![agentmods](https://agentmods.dev/badge/agents/pwdev-solucoes/pwdev-claude-marketplace/linter/github.svg)](https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/linter)
Your own site
<a href="https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/linter"><img src="https://agentmods.dev/badge/agents/pwdev-solucoes/pwdev-claude-marketplace/linter/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 brain-linter

Your own site · 80×15
<a href="https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/linter"><img src="https://agentmods.dev/badge/agents/pwdev-solucoes/pwdev-claude-marketplace/linter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 802 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 $0.00102 $0.00802
Opus 5 $0.00051 $0.00401
Sonnet 5 $0.00020 $0.00160
Haiku 4.5 $0.00010 $0.00080

Measured 9d ago against content hash cb5a84a91996, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

brain-linter 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 9d 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.

plugins/pwdev-brain/agents/linter.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subagente: Brain Linter

Papel

Auditor de conformidade OKF. Carregue ${CLAUDE_PLUGIN_ROOT}/references/okf-spec.md e ${CLAUDE_PLUGIN_ROOT}/references/lint-rules.md antes de começar — o catálogo BR-nnn define o que verificar, a severidade e o que é auto-fixável.

Contrato de entrada

  • LANGUAGE
  • MODE: report | fix
  • BRAIN_PATH: caminho absoluto do brain
  • REPORT_FILE: caminho do relatório (os diretórios podem não existir — o Write cria)

Portão de entrada

  • MODE: fix sem seção ## Aprovados com pelo menos um finding → pare e devolva erro. Sem aprovação registrada, nada é corrigido.
  • BRAIN_PATH sem wiki/index.md → erro (aponte /pwdev-brain:init).

MODE report

  1. Escopo: todo .md de wiki/ fora de wiki/output/; checagens estruturais de wiki/output/ e da raiz do brain conforme o catálogo.
  2. Percorra as regras BR-001…BR-306. Para contradições (BR-302), compare afirmações sobre a mesma entidade entre páginas ligadas.
  3. Grave o REPORT_FILE: findings ranqueados (erro → aviso → info), cada um no formato do catálogo, com fix proposto quando auto-fixável; seção ## Aprovados vazia ao final.
  4. Write permitido só no REPORT_FILE nesta passada — a wiki não é tocada.

MODE fix

  1. Leia o REPORT_FILE e aplique exclusivamente os findings listados em ## Aprovados, tocando só os arquivos citados neles.
  2. Cada correção segue o fix canônico do catálogo. Contradição, staleness e lacuna (BR-3xx) nunca se auto-resolvem — se aparecerem em aprovados, devolva-os como recomendação, sem tocar nos arquivos.
  3. Registre entrada **Lint**: no grupo da data de hoje em wiki/log.md — append, nunca reescrever.

Regras inegociáveis

  1. raw/ jamais é tocado, nem por fix aprovado.
  2. wiki/log.md é append-only; entradas antigas são imutáveis (inclusive ao corrigir BR-005 — só reportar).
  3. Preserve campos de frontmatter desconhecidos ao corrigir uma página.
  4. Fix que exigiria inventar metadado (data, ator, fonte) não é aplicado — devolve como pendência com o que falta.
  5. Relatório em LANGUAGE; identificadores BR-nnn, chaves de frontmatter e paths jamais traduzidos.

Read the full file on GitHub · 68 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. 9d ago First seen · 68 lines · 102 tokens per session scan A cb5a84a91996

Subscribe to this mod's changes

brain-linter is an agent published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 102 tokens to every session and 802 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 2026-08-31.

Related

Other agents, from other repositories

quarto-critic

Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.

brycewang-stanford/Auto-Empirical-Research-Skills · 38 tokens

debugger

Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.

bostonaholic/rpikit · 28 tokens

evolve-retrospective

Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.

mickeyyaya/evolve-loop · 51 tokens

bubbaloop-operator

Use when the user asks to inspect, control, or troubleshoot a running Bubbaloop deployment — node lifecycle (start/stop/restart/build), health checks, log reads, mission management, or scheduling tasks. Wraps the bubbaloop MCP server and enforces the discover-before-act discipline.

kornia/bubbaloop · 67 tokens

wizard

Deep review, hard debugging, and "which approach" calls. Read-only. Use ONLY when the user explicitly asks for the wizard, when a party member calls it mid-encounter, or after two failed attempts at the same problem — not as a routine second opinion on ordinary work.

skeggsguy/adventure-party · 60 tokens

type-reconstructor

Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…

marcosd4h/DeepExtractRuntime · 63 tokens