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.
git clone --depth 1 https://github.com/6eanut/llm-wikiWrote 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/6eanut/llm-wiki/wiki-ingest)<a href="https://agentmods.dev/commands/6eanut/llm-wiki/wiki-ingest"><img src="https://agentmods.dev/badge/commands/6eanut/llm-wiki/wiki-ingest.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.00285 |
| Opus 5 | $0.00009 | $0.00143 |
| Sonnet 5 | $0.00004 | $0.00057 |
| Haiku 4.5 | $0.00002 | $0.00028 |
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 7d 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.
What it actually says
Ingest a Source into the Wiki
The user ran /wiki-ingest $ARGUMENTS.
Key Paths
- Wiki root:
./wiki/(or$LLM_WIKI_ROOT) - Source files:
./.raw/ - Skill directory:
~/.claude/skills/llm-wiki/
Procedure
1. Verify wiki exists
Check ./wiki/.llm-wiki/index.md. If not found, offer to run init-wiki.sh.
2. Identify and hash the source
- If file path: run
~/.claude/skills/llm-wiki/scripts/hash-files.sh <path> - If URL: use WebFetch to retrieve, then compute SHA-256
3. Check if already ingested
Look for sentinel: ./wiki/.llm-wiki/cache/ingests/$HASH.done
4. Load the full workflow
Use Skill("llm-wiki") to load the complete ingestion procedure from workflows/ingest.md, which covers:
- Language detection
- Concept/person/article extraction
- Contradiction detection
- Two-phase generation with user review checkpoints
- Index regeneration
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.
- 7d ago First seen · 40 lines · 18 tokens per session scan A 512b8e7984be
wiki-ingest is a command published in the GitHub repository 6eanut/llm-wiki (44 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 285 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 2026-08-30.
Other commands, from other repositories
contribute
Add a thought, source, or paste. Use --project/-p to target another project without switching current. Usage: /mb:contribute [-p ] [--mode daily|concept|daily+concept].
build
Rebuild context.md for a project from sources/. Usage: /mb:build [-p ] [project-id].
init
Scaffold a new MindBase project (v2 layout). Usage: /mb:init [template] [-- mission ...].
new-project
Create a new project with template choice — interactive flow. Usage: /mb:new-project [template].
research
Deep research on a topic — web + existing wiki + synthesis → sources/research/. Usage: /mb:research [-p ].
ask
Query the MindBase wiki — cited answer using hybrid search + graph expansion. Usage: /mb:ask [-p ] [--all-projects].