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.
npx agentmods add commands/frankchu91/mindbase-llm-wiki/askgit clone --depth 1 https://github.com/frankchu91/mindbase-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/frankchu91/mindbase-llm-wiki/ask)<a href="https://agentmods.dev/commands/frankchu91/mindbase-llm-wiki/ask"><img src="https://agentmods.dev/badge/commands/frankchu91/mindbase-llm-wiki/ask.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 | $0.00036 | $0.00509 |
| Opus 5 | $0.00018 | $0.00254 |
| Sonnet 5 | $0.00007 | $0.00102 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
ask 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 5d 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
Query the user's MindBase wiki.
Arguments: $ARGUMENTS
Parse:
--project <id>or-p <id>flag → target project id (mutually exclusive with--all-projects).--all-projectsflag → search across all projects, not just current.- Remaining text = the question.
If both --project and --all-projects provided, tell the user to pick one. If question empty, ask "What do you want to know about your wiki?"
Procedure:
- Call
mindbase_search_wiki({ query, projectId?, limit: 8 })for fast keyword candidates. - Call
mindbase_ask_wiki({ query, projectId? })for graph-aware retrieval (top hits + 1-hop wikilink neighbors). - Read the top 3-5 hits via
mindbase_read_wiki_page({ slug }). - Synthesize a cited answer. Inline citations as
[<slug>:<line-range>]. List sources at the end with full paths. - If
--all-projects, usemindbase_search_all_projectsinstead of the per-project tools in steps 1-2.
projectId in the MCP calls: pass user's -p value; if -p absent AND --all-projects absent, MCP tools default to config.json currentProjectId. -p does NOT change current project.
After answering, ASK the user: "Save this answer as a wiki page?" If yes, call mindbase_save_chat_excerpt or mindbase_contribute (mode=concept, pass same projectId) to file it back. This is the Karpathy "good answers compound" loop.
Do not invent facts. If the wiki doesn't contain the answer, say so explicitly — never silently fall back to general knowledge.
Examples:
/mb:ask "how did I resolve auth ambiguity"→ current project/mb:ask -p ai-agents "what's my stance on agent marketplaces"→ ai-agents/mb:ask --all-projects "RAG vs fine-tuning"→ all projects
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.
- 5d ago First seen · 33 lines · 36 tokens per session scan A eacde455e56f
ask is a command published in the GitHub repository frankchu91/mindbase-llm-wiki (93 stars, last pushed 11d ago), licensed MIT. It adds 36 tokens to every session and 509 once invoked, about $0.0002 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
wiki-query
Ask questions against the wiki. Synthesizes answers from wiki pages with cross-reference citations.
wiki-req
Capture and decompose a concept into atomic, traceable wiki requirements. Clarifies ambiguous requirements, splits them into atomic pieces, and persists them as wiki/requirements/ pages with status tracking.
wiki-ingest
Process new source packets and synthesize them into wiki knowledge pages.
wiki-record
Capture the just-completed task's tool-call trajectory into the wiki as agent working-memory, then optionally distill it into a reusable skill.
wiki-retro
Save an atomic insight from the current task into the wiki. Creates a single markdown file that layered recall surfaces in future sessions.
wiki-discover
Auto-discover new sources from the web. Searches based on config topics and known knowledge gaps.