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 skills add po4yka/llm-wiki-skills --skill llm-wiki-doctorgit clone --depth 1 https://github.com/po4yka/llm-wiki-skillsWrote 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/po4yka/llm-wiki-skills/llm-wiki-doctor)<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-doctor"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-doctor/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/po4yka/llm-wiki-skills/llm-wiki-doctor"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-doctor.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 | $0.00058 | $0.00836 |
| Opus 5 | $0.00029 | $0.00418 |
| Sonnet 5 | $0.00012 | $0.00167 |
| Haiku 4.5 | $0.00006 | $0.00084 |
Grade A, and why
llm-wiki-doctor 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM-Wiki Doctor
Goal
Run a read-only diagnostic pass over an existing document collection and produce an adoption scorecard.
When to use
Use before migration, refactoring, setup, or trust work when the user already has material and wants to know where to start.
Inputs
- Path to the workspace root to diagnose (repository, vault, or docs folder).
- Whether the user expects read-only mode or has already granted write access (default: read-only).
- Any existing
AGENTS.md,CLAUDE.md,.cursorrules, or project-instruction files to inspect for context. - Optional scope hint (a specific subfolder, domain, or wiki space) when the workspace is too large to inventory in full.
Procedure
1. Preflight
Identify the workspace root and check whether the user requested read-only mode. Default to read-only.
Inspect, when present:
AGENTS.md,CLAUDE.md,.cursorrules,.cursor/rules, project instructions;raw/,wiki/,inbox/,_meta/,_agent/;- Obsidian files such as
.obsidian/, wikilinks and attachments; - README, ADRs, docs folders and existing indexes.
2. Inventory
Because file state can drift between invocation and reporting, re-verify counts and examples against the current workspace before finalizing the scorecard rather than trusting a cached impression.
Collect counts and examples for:
- Markdown pages;
- raw sources and assets;
- generated pages;
- pages with frontmatter;
- pages with wikilinks/backlinks;
- pages that look like synthesis;
- files that mix source material and conclusions.
3. Score readiness
Score 0-5:
| Area | What to check |
|---|---|
| Structure | raw/wiki/schema separation, predictable folders, index/log. |
| Provenance | source links, source hashes, claim support. |
| Retrievability | index, titles, links, tags, searchability. |
| Trust | lifecycle states, review gates, protected sections. |
| Migration risk | broken links, attachments, generated content, sensitive data. |
4. Detect anti-patterns
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 · 116 lines · 58 tokens per session scan A d7eccbb3454f
llm-wiki-doctor is a skill published in the GitHub repository po4yka/llm-wiki-skills (3 stars, last pushed 19d ago), licensed MIT. It adds 58 tokens to every session and 836 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 2026-08-31.
Other skills, from other repositories
wiki-export
Export a vault's wiki either as a single portable file (llms.txt or llms-full.txt per the llmstxt.org standard) or as an OKF knowledge bundle (Google's Open Knowledge Format v0.1 — a shareable directory of markdown files any AI agent can consume). Use when the user says "export my wiki", "make an llms.txt", "share my…
template-execute
Execute a Templater template, optionally writing the rendered output to a new file. Arguments are exposed to the template via tp.mcpTools.prompt("key") (directly under tp, NOT under tp.user — easy footgun). EN triggers: "render the X template", "run the daily template", "execute Templates/X.md with arg1=v1", "use…
read-frontmatter
Read frontmatter (the whole object or one key) from a file. Types are preserved (numbers stay numbers, arrays stay arrays). EN triggers: "what's the frontmatter of X", "show me the metadata of X", "read the properties of X", "what's the status of X", "get the tags on X". FR triggers : "quel est le frontmatter de X"…
read-get
Read the full content of a file from a vault (markdown + frontmatter). EN triggers: "show me X", "open the file X", "read X", "what's in X.md", "fetch X". FR triggers : "montre-moi X", "ouvre le fichier X", "lis X", "qu'est-ce qu'il y a dans X.md", "récupère X". Example / Exemple: EN: "show me Sessions/2026-05-03.md"…
ingest
A tool for adding a URL, file, text, or Inbox item to the LLM Wiki. It checks the material's purpose, preserves the original source, compiles a wiki page, updates indexes and logs, and reviews the result.
okf
Author, maintain, and consume Open Knowledge Format (OKF) knowledge bundles — portable markdown + YAML frontmatter that both humans and agents read. Use when capturing project knowledge (services, APIs, schemas, metrics, runbooks, decisions) into an OKF bundle, when updating one after code or docs change, or when a…