Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/vanillaflava/llm-wiki-skills/wiki-config)<a href="https://agentmods.dev/skills/vanillaflava/llm-wiki-skills/wiki-config"><img src="https://agentmods.dev/badge/skills/vanillaflava/llm-wiki-skills/wiki-config/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/skills/vanillaflava/llm-wiki-skills/wiki-config"><img src="https://agentmods.dev/badge/skills/vanillaflava/llm-wiki-skills/wiki-config.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 | $0.00166 | $0.04269 |
| Opus 5 | $0.00083 | $0.02135 |
| Sonnet 5 | $0.00033 | $0.00854 |
| Haiku 4.5 | $0.00017 | $0.00427 |
Grade A, and why
wiki-config 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 12d 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 — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Config
Interactive setup, validation, and maintenance for wiki-config.md. Pairs with the five operational wiki skills (wiki-ingest, wiki-lint, wiki-integrate, wiki-crystallize, wiki-query) which all read the same config.
Capability Requirements
Filesystem read, write, search, and directory creation. If running on a surface without filesystem tools, inform the user and stop.
Workflow
Step 0 - Welcome & Initialization
Every time wiki-config is invoked, start here.
Show the wiki skill ecosystem
Check which wiki skills are available in this session. Scan the <available_skills> section in your context for skills matching the wiki-* pattern (wiki-config, wiki-ingest, wiki-query, wiki-lint, wiki-integrate, wiki-crystallize). Skills found in <available_skills> are enabled and usable - mark as ✓. Skills not found are either not installed or toggled off in the user's settings - mark as ✗.
Present this table with actual status for each skill:
## Wiki Skill Ecosystem
| Skill | Status | What it does |
|---|---|---|
| wiki-config | ✓ | Interactive setup and validation |
| wiki-ingest | [✓/✗] | Process raw/ → wiki pages → ingested/ |
| wiki-query | [✓/✗] | Search wiki, cite sources, file good answers |
| wiki-lint | [✓/✗] | Health checks: broken links, orphans |
| wiki-integrate | [✓/✗] | Add backlinks when pages change |
| wiki-crystallize | [✓/✗] | Distil conversations into wiki pages |
If any are missing: "Install from https://github.com/vanillaflava/llm-wiki-skills for the full ecosystem."
The bundled references/setup-help.md is available throughout this session. Read it if you need more orientation context, if a user asks detailed questions about the wiki system, or if you get stuck.
Present the welcome message
"Let me read the setup guide to orient us both..."
Then present:
Welcome to your LLM-Wiki
Before we start, a quick orientation:
Filesystem access scope - The directory your filesystem tool can reach. This is the outer boundary. Scope your tool tightly; broad access is a privacy risk.
Wiki root - The folder inside that scope containing your Markdown notes and wiki system files (
wiki-config.md,wiki-help.md,Home.md,Overview.md,index.md,log.md,raw\,ingested\,templates\). This is where you keep your.mdfiles - a subset of your Obsidian vault, your Logseq graph, or wherever you maintain notes. Skills find wiki root by looking forwiki-config.md.
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/templates/config.md 175 B
- assets/templates/domain-home.md 1.7 KB
- assets/templates/established-patterns.md 726 B
- assets/templates/home.md 3.0 KB
- assets/templates/index.md 761 B
- assets/templates/knowledge.md 791 B
- assets/templates/log.md 421 B
- assets/templates/longform.md 1.4 KB
- assets/templates/note.md 171 B
- assets/templates/overview.md 1.0 KB
- assets/templates/profile.md 876 B
- assets/templates/reference.md 604 B
- assets/templates/survey.md 1.3 KB
- assets/wiki-config-template.md 3.8 KB
- assets/wiki-help.md 25 KB
- assets/wiki-schema.md 6.7 KB
- references/setup-help.md 6.2 KB
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.
- 12d ago First seen · 314 lines · 166 tokens per session scan A 95f59f177ba3
wiki-config is a skill published in the GitHub repository vanillaflava/llm-wiki-skills (64 stars, last pushed 2mo ago), licensed MIT. It adds 166 tokens to every session and 4,269 once invoked, about $0.0008 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 skills, from other repositories
llm-wiki
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).
mindbase
Maintain a persistent AI-tended research wiki. Activates when the user wants to ingest a source (PDF, URL, article, paste), capture a thought, build the wiki context, query what's already known, lint for orphans/contradictions, or maintain page conventions. Phrases include "add this to my wiki", "today I decided…"…
llm-wiki-pm
Persistent PM knowledge base, competitive intel, customer notes, strategy, roadmap, AI market. Markdown wiki with entities, concepts, comparisons. Ingest sources, query, update with diffs, lint. Fires on "remember that / note that / don't forget / what do we know about X / what am I missing / blind spots".
llm-wiki-brief
Structured daily/weekly briefs, tag digests, and check-ins from the PM wiki. Richer output than core catch-me-up.
llm-wiki-crm
PM relationship CRM layer on top of the wiki. Relationship health, auto-enrichment via web search, account health tracking, and people profile maintenance. Does not replace Salesforce — tracks PM-specific context (product feedback, feature asks, strategic relationship, communication history).
llm-wiki-research
Research sprints, competitive deep dives, and auto-enrichment of stub wiki pages. Delegates web fetching to worker-source-fetcher. Files all findings back into the wiki.