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.
/plugin marketplace add pwdev-solucoes/pwdev-claude-marketplace/plugin install pwdev-brainWrote 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.
[](https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/ingest)<a href="https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/ingest"><img src="https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/ingest/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.
<a href="https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/ingest"><img src="https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00026 | $0.00836 |
| Opus 5 | $0.00013 | $0.00418 |
| Sonnet 5 | $0.00005 | $0.00167 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
ingest 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pwdev-brain:ingest
Princípio: o comando conversa, o subagente grava. A discussão exigida
pela spec acontece aqui na sessão principal; a leitura pesada da fonte e a
escrita na wiki ficam no subagente brain-ingestor, em duas passadas.
STEP 0 — Idioma
${CLAUDE_PLUGIN_ROOT}/references/language.md
Gate
Sem .claude/pwdev-brain-context.md ou sem <brain>/wiki/index.md válido →
aborte e aponte /pwdev-brain:init.
STEP 1 — Normalizar a fonte
$ARGUMENTS (se vazio, pergunte o que ingerir):
- Arquivo já em
raw/→ usar como está. - Caminho externo → copiar para
<brain>/raw/<nome>(avisar o usuário; nunca mover nem alterar o original). - URL → WebFetch e salvar como
<brain>/raw/<slug>.mdcom cabeçalho de proveniência (URL canônica e data de captura ISO 8601).
raw/ é imutável: arquivo que já existe lá nunca é editado ou
sobrescrito — nome em conflito ganha sufixo.
STEP 2 — Passe extract (subagente)
Despache brain-ingestor com:
LANGUAGE: {{lang}}
MODE: extract
BRAIN_PATH: {{caminho absoluto}}
SOURCE_FILE: {{raw/arquivo}}
HANDOFF_FILE: .claude/pwdev-brain/ingest-{{YYYY-MM-DD}}-{{slug}}.md
USER_ACTOR: human:{{id}}
PROCESS_ACTOR: pwdev-brain/1.0.0
Ele lê a fonte inteira + wiki/index.md + conceitos relacionados e grava a
proposta no HANDOFF_FILE — nada é escrito em wiki/ nesta passada.
STEP 3 — Discussão (o coração da operação)
Apresente a proposta ao usuário conforme a preferência do contexto:
- ponto-a-ponto — cada ponto extraído: aprovar / editar / descartar.
- lote — a lista completa de uma vez, com aprovação única e ajustes.
Registre cada decisão na seção ## Decisões do HANDOFF_FILE (aprovado /
editado com o novo texto / descartado). Pontos que o usuário confirmar
como corretos podem receber verified — marque isso explicitamente.
STEP 4 — Passe apply (subagente)
Despache brain-ingestor de novo, mesmo bloco de entrada com
MODE: apply. Ele grava/atualiza conceitos, links, wiki/index.md e
wiki/log.md seguindo estritamente as decisões do handoff.
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.
- 9d ago First seen · 79 lines · 26 tokens per session scan A d690fa888a63
ingest is a command published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 26 tokens to every session and 836 once invoked, about $0.0001 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.