A command that imports project or topic information into an LLM Wiki, a local knowledge base for language-model work. It gathers sources, saves an unchanged raw record, and updates a project wiki page.

Use it to ingest a project's recent Git history and status files, or to record decisions and lessons learned in a local wiki.

It reduces the manual work of collecting project status, recent changes, decisions, and lessons in one place. Keeping raw material separate preserves the original gathered information.

kb-ingest — Command for Claude Code by thomascasali

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/thomascasali/claude-kb-workflow

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/thomascasali/claude-kb-workflow/kb-ingest/github.svg)](https://agentmods.dev/commands/thomascasali/claude-kb-workflow/kb-ingest)

Your own site

<a href="https://agentmods.dev/commands/thomascasali/claude-kb-workflow/kb-ingest"><img src="https://agentmods.dev/badge/commands/thomascasali/claude-kb-workflow/kb-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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/thomascasali/claude-kb-workflow/kb-ingest"><img src="https://agentmods.dev/badge/commands/thomascasali/claude-kb-workflow/kb-ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 805 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	$0.00000	$0.00805
Opus 5	$0.00000	$0.00402
Sonnet 5	$0.00000	$0.00161
Haiku 4.5	$0.00000	$0.00081

Measured 9d ago against content hash d83bb64a0968, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

kb-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/kb-ingest.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/kb-ingest — Ingest sessione nella LLM Wiki

Esegui un ingest nella LLM Wiki per il progetto o argomento specificato: $ARGUMENTS

Path della Wiki: questa skill assume la variabile $LLM_WIKI_PATH puntata alla tua wiki locale (es. ~/llm-wiki/ o D:/percorso/llm-wiki/). Imposta la variabile in .env o nel CLAUDE.md del workspace.

Steps

Leggi schema $LLM_WIKI_PATH/schema.md per le convenzioni
Raccogli sorgenti in base all'argomento:
- Se è un progetto (es. nome-progetto):
  - git -C <path-progetto> log --oneline -10
  - Leggi CURRENT_STATUS.md se esiste
  - Leggi CLAUDE.md header per stato corrente
- Se è decision [titolo]: usa le note fornite dall'utente
- Se è lesson [descrizione]: usa la descrizione del bug/problema risolto
Salva raw in $LLM_WIKI_PATH/raw/ con nome YYYY-MM-DD-[slug].md:
- Formato: metadata header (fonte, data raccolta) + contenuto grezzo
- NON modificare mai i file in raw/ dopo la creazione
Aggiorna wiki page $LLM_WIKI_PATH/wiki/projects/[progetto].md:
- Crea se non esiste, aggiorna se esiste
- Struttura: Quick Reference → Stato Corrente → Lezioni Apprese → Open Questions → Link KB
- Mantieni la storia: non cancellare sezioni passate, aggiungi sotto
- ⚠️ Sintassi link obbligatoria per Obsidian (se usi Obsidian come vault):
  - Link interni wiki: [[nome-pagina]] o [[nome-pagina|Testo]]
  - Link esterni (KB stabile, GitHub, docs): markdown standard [testo](url)
- Frontmatter obbligatorio all'inizio del file:
```
**Aggiornato**: YYYY-MM-DD
**Stack**: [tecnologie principali]
**Tags**: #progetto #[stack-tag]
```
Se emergono pattern nuovi: crea/aggiorna $LLM_WIKI_PATH/wiki/concepts/[concetto].md
- Usa [[wikilink]] per linkare i progetti che usano quel concetto
- Aggiungi il concetto all'indice in wiki/index.md
Aggiorna $LLM_WIKI_PATH/wiki/index.md:
- Aggiorna la riga del progetto nella tabella con data odierna e sommario

Read the full file on GitHub · 60 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.

9d ago First seen · 60 lines · 0 tokens per session scan A d83bb64a0968

Subscribe to this mod's changes

kb-ingest is a command published in the GitHub repository thomascasali/claude-kb-workflow (2 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 805 tokens. 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.

Claude Code Memory and context ai-agents claude-code-agents claude-code-skills italiano knowledge-base

wiki

Run the LLM Wiki — initialize, ingest, curate, or query. The plugin probes vault state and chooses the right next step.

odere-pro/claude-wiki-pages-plugin · 27 tokens

wiki-digest

Generate a daily or weekly digest of wiki changes — new sources, pages, insights, and gaps.

zosmaai/pi-llm-wiki · 20 tokens

wiki-status

Show wiki health overview — source count, page stats, orphan count, last activity dates.

zosmaai/pi-llm-wiki · 18 tokens

ccr

CCR (Compressed Context with Retrieval) — recall the full original of context that greatcto compressed/filtered out, by its short id. The retrieval half of the compression layer.

avelikiy/great_cto · 36 tokens

ask

Query the MindBase wiki — cited answer using hybrid search + graph expansion. Usage: /mb:ask [-p ] [--all-projects].

frankchu91/mindbase-llm-wiki · 36 tokens

recap

Summarize what happened in the project since a given date. Produces a short lead on what's different now, backed by tables and lists covering completed work, state changes, backlog movement, and key decisions. Use when the user wants to catch up on project activity, review recent progress, or generate a status update…

OdinMB/ops-workflow · 105 tokens