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 skills/oshayr/llm-wiki/readnpx skills add Oshayr/LLM-Wiki --skill readgit clone --depth 1 https://github.com/Oshayr/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/skills/oshayr/llm-wiki/read)<a href="https://agentmods.dev/skills/oshayr/llm-wiki/read"><img src="https://agentmods.dev/badge/skills/oshayr/llm-wiki/read.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 | $0.00102 | $0.00746 |
| Opus 5 | $0.00051 | $0.00373 |
| Sonnet 5 | $0.00020 | $0.00149 |
| Haiku 4.5 | $0.00010 | $0.00075 |
Grade A, and why
wiki-read 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.
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.
Wiki Read
Ask the wiki a question and get a cited answer. If the wiki doesn't have the answer, automatically researches using whatever tools are available, ingests the results, and answers from the new pages.
Resolve .wiki/ from plugin install scope. If not found, say "No wiki found. Use /wiki-write to create one."
Arguments
/wiki-read <question>— standard: search wiki first, research if not found, answer with citations/wiki-read quick <question>— index scan only, no research fallback (fastest)/wiki-read deep <question>— full wiki search + raw sources + automatic multi-channel research if needed (most thorough)
Process
Launch the wiki-reader agent with the question and depth level.
Standard depth (default)
- Read
.wiki/index.md, identify 2-4 relevant pages - Use
bin/search-fulltext.pyfor ranked results - Read the relevant pages, synthesize a cited answer with
[[slug]]references - If NOT found or insufficient: automatically research using whatever tools are available:
- Discover available tools at runtime (WebSearch, WebFetch,
wiki_wikipedia_searchfor factual/encyclopedic topics, any MCP tools like Perplexity, Context7, etc.) - Search using available tools, fetch and extract content
- Ingest results via
wiki-writeragent (mode: ingest) - Answer from the newly created pages with
[[slug]]citations - Note: "Researched fresh and saved to wiki."
- Discover available tools at runtime (WebSearch, WebFetch,
- Offer to save analysis as a wiki page if the answer is substantial
Quick depth
- Read
.wiki/index.mdonly - Scan for matching slugs/titles by text match
- Return: list of relevant pages with one-line descriptions
- No page content read, no research fallback — fastest possible response
- If not found, suggest running standard
/wiki-read
Deep depth
Everything in standard, plus:
- Search
.wiki/raw/for source materials matching the query - Cross-reference raw sources with compiled pages
- Use all available tools iteratively for multi-channel research if needed
- Most thorough — uses the most context
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 · 60 lines · 102 tokens per session scan A 0aeaed29e18d
wiki-read is a skill published in the GitHub repository Oshayr/LLM-Wiki (49 stars, last pushed 4mo ago), licensed MIT. It adds 102 tokens to every session and 746 once invoked, about $0.0005 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 an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gist. Use this skill whenever the user wants to ingest a source (paper, article, transcript, PDF, notes) into a persistent compounding knowledge base, ask a question against accumulated notes, lint or…
citation-audit
Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations. Use when user says "审查引用", "check citations"…
paper-illustration
Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.
research-refine
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.6-Sol review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that…
resubmit-pipeline
Workflow 5: orchestrate a text-only resubmit of a polished paper to a different venue under hard constraints (no new experiments, no bib edits, no framework changes, never overwrite prior submissions). Use when user says "resubmit pipeline", "重投流程", "port paper to ", "resubmit to ", "tighten paper for resubmission"…
rebuttal
Workflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds. Use when user says "rebuttal", "reply to reviewers", "ICML rebuttal", "OpenReview response", or wants to answer external reviews safely.