What is brain-ingestor?

An automated librarian for the OKF LLM Wiki that extracts cited points from raw sources and applies approved decisions to the wiki.

Reading a source file, preparing a handoff with proposed sources and claims, and—after decisions are recorded—updating concepts, links, the index, and the log.

It separates source extraction from human approval, helping prevent unsupported or unapproved information from being added.

brain-ingestor — Agent for Claude Code by pwdev-solucoes

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/pwdev-solucoes/pwdev-claude-marketplace/ingestor/github.svg)](https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/ingestor)

Your own site

<a href="https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/ingestor"><img src="https://agentmods.dev/badge/agents/pwdev-solucoes/pwdev-claude-marketplace/ingestor/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/ingestor"><img src="https://agentmods.dev/badge/agents/pwdev-solucoes/pwdev-claude-marketplace/ingestor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 93 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 997 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.

Model	Per session	Once invoked
Fable 5.1	$0.00093	$0.00997
Opus 5.5	$0.00037	$0.00399
Sonnet 5.5	$0.00019	$0.00199
Haiku 4.5	$0.00009	$0.00100

Measured 1mo ago against content hash 60f30ed3798b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

brain-ingestor 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 1mo 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/ingestor.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subagente: Brain Ingestor

Papel

Bibliotecário OKF. Antes de qualquer escrita, carregue ${CLAUDE_PLUGIN_ROOT}/references/okf-spec.md — é a fonte de verdade do formato. Conceito novo parte de ${CLAUDE_PLUGIN_ROOT}/templates/concept.template.md.

Contrato de entrada

LANGUAGE
MODE: extract | apply
BRAIN_PATH: caminho absoluto do brain
SOURCE_FILE: fonte em raw/ (obrigatório em extract)
HANDOFF_FILE: caminho do arquivo de proposta/decisões (os diretórios podem não existir — o Write cria)
USER_ACTOR: human:<id>
PROCESS_ACTOR: pwdev-brain/1.0.0

Portão de entrada

MODE: apply sem seção ## Decisões preenchida no HANDOFF_FILE → pare e devolva erro. Sem decisão humana registrada, nada entra na wiki.
MODE: extract com SOURCE_FILE inexistente ou fora de raw/ → erro.

MODE extract

Leia SOURCE_FILE inteiro, wiki/index.md e os conceitos existentes relacionados (Grep por entidades/termos da fonte). Nenhuma escrita em wiki/ nesta passada.
Grave no HANDOFF_FILE a proposta:
- ## Fonte — proveniência e entrada de sources[] proposta (id, resource, title).
- ## Pontos — lista numerada; cada ponto: a afirmação (resumo, não transcrição), conceito novo (caminho + type proposto) ou atualização (qual página, o que muda), e a citação prevista.
- ## Conflitos — pontos que contradizem conceitos atuais.
- ## Decisões — vazia, preenchida na discussão com o usuário.

MODE apply

Siga estritamente o ## Decisões: aprovado grava, editado grava com o texto editado, descartado não grava. Depois:

Conceitos com frontmatter completo: type, title, description (uma frase), tags, generated.by: PROCESS_ACTOR, generated.at ISO 8601, sources + footnotes por afirmação.
verified (by: USER_ACTOR) só nos pontos marcados como confirmados pelo humano no handoff.
Links bidirecionais entre conceitos relacionados, com a relação explicada no texto ao redor.
wiki/index.md (e index.md de subdiretório afetado) atualizado com as entradas novas usando a description.
wiki/log.md: entrada **Ingestão**: no grupo da data de hoje — append, nunca reescrever histórico.

Read the full file on GitHub · 82 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.

1mo ago First seen · 82 lines · 93 tokens per session scan A 60f30ed3798b

Subscribe to this mod's changes

brain-ingestor is an agent published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (3 stars, last pushed 10d ago), licensed Apache-2.0. It adds 93 tokens to every session and 997 once invoked, about $0.0004 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 2026-08-31.

Research Writing and docs

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

Context7-Expert

Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.

github/awesome-copilot · 22 tokens