wiki-ingest

wiki-ingest is a command for Claude Code from ricneves-ai/flowgrammers-skills. It costs 63 tokens per session (652 once invoked), scanned A, original, MIT.

A workflow for adding a raw source file to an LLM Wiki, a collection of linked research notes. It reads the source, creates a summary page, updates related pages and the index, and records the change in the log.

In plain words
What is it for?
Use it to ingest papers or articles, discuss their main claims, update related concepts and entities, flag contradictions, and maintain wiki references.
Why use it?
It keeps new research connected to existing notes instead of leaving it as an isolated document.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it to ingest papers or articles, discuss their main claims, update related concepts and entities, flag contradictions, and maintain wiki references.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ricneves-ai/flowgrammers-skills/wiki-ingest
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 wiki-ingest

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

agentmods 80×15 button for wiki-ingest

Your own site · 80×15
<a href="https://agentmods.dev/commands/ricneves-ai/flowgrammers-skills/wiki-ingest"><img src="https://agentmods.dev/badge/commands/ricneves-ai/flowgrammers-skills/wiki-ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 652 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 $0.00063 $0.00652
Opus 5 $0.00032 $0.00326
Sonnet 5 $0.00013 $0.00130
Haiku 4.5 $0.00006 $0.00065

Measured 9d ago against content hash a8980866f8c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

wiki-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.

commands/wiki-ingest.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/wiki-ingest

Ingere uma nova fonte no LLM Wiki. Este é o comando mais utilizado.

O fluxo: lê a fonte → discute o TL;DR e as principais afirmações com você → escreve uma página de resumo da fonte → atualiza todas as páginas de entidades e conceitos relevantes → sinaliza contradições → atualiza index.md → adiciona entrada ao log.md.

Uma ingestão típica toca 5 a 15 páginas do wiki. Você (o usuário) participa do processo: o ingestor propõe alterações e aguarda sua confirmação antes de escrever.

Uso

/wiki-ingest <caminho>
/wiki-ingest raw/papers/monosemanticity.pdf
/wiki-ingest raw/articles/2026-04-01-post-interpretabilidade.md

O que acontece

  1. Preparo — executa scripts/ingest_source.py para obter título, prévia e caminho sugerido para o resumo
  2. Leitura — lê a fonte diretamente
  3. Discussão — reporta TL;DR, principais afirmações, quais páginas serão tocadas, possíveis contradições
  4. Confirmação — aguarda seu aval (ou redirecionamento)
  5. Escrita — cria o resumo da fonte, atualiza 5 a 15 páginas, sinaliza contradições
  6. Índice — executa scripts/update_index.py ou edita wiki/index.md diretamente
  7. Log — executa scripts/append_log.py --op ingest --title "<título>"
  8. Relatório — lista com wikilinks de todas as páginas tocadas

Sub-agente

Este comando despacha o sub-agente wiki-ingestor para o trabalho pesado. Veja agents/wiki-ingestor.md.

Scripts

  • engineering/llm-wiki/scripts/ingest_source.py — preparação da fonte (metadados + prévia)
  • engineering/llm-wiki/scripts/update_index.py — regenera o índice
  • engineering/llm-wiki/scripts/append_log.py — registra a ingestão no log

Regras

  • A fonte deve estar dentro da camada raw/ do vault. Se não estiver, o comando pedirá que você a mova primeiro.
  • raw/ é imutável — o ingestor apenas lê.
  • Se uma página de resumo já existir, o ingestor entra em modo mesclagem e acrescenta uma seção de re-ingestão.

Referência de Skill

Read the full file on GitHub · 53 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 · 53 lines · 0 tokens per session scan A a8980866f8c0

Subscribe to this mod's changes

wiki-ingest is a command published in the GitHub repository ricneves-ai/flowgrammers-skills (112 stars, last pushed 3mo ago), licensed MIT. It adds 63 tokens to every session and 652 once invoked, about $0.0003 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.