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/maintainnpx skills add Oshayr/LLM-Wiki --skill maintaingit 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/maintain)<a href="https://agentmods.dev/skills/oshayr/llm-wiki/maintain"><img src="https://agentmods.dev/badge/skills/oshayr/llm-wiki/maintain.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 | $0.00061 | $0.00900 |
| Opus 5 | $0.00030 | $0.00450 |
| Sonnet 5 | $0.00012 | $0.00180 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade A, and why
wiki-maintain 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 6d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Maintain
Comprehensive wiki maintenance: lint, deduplicate, upgrade, and analyze.
Resolve .wiki/ from plugin install scope. If not found, say "No wiki found."
Arguments
/wiki-maintain— run full maintenance (all steps below)/wiki-maintain lint— only fix broken links, missing frontmatter, orphans/wiki-maintain dedup— only find and merge near-duplicate pages/wiki-maintain gaps— only analyze knowledge gaps and missing coverage
Full Maintenance Steps
1. Lint
Launch wiki-auditor agent to:
- Find
[[wiki-links]]that point to non-existent pages — list for user - Fix missing frontmatter fields (add defaults)
- Find orphan pages (no incoming links) — suggest connections
- Remove dead index entries
- Fix stale
updated:dates on pages that were modified but not date-bumped
2. Deduplicate
Find pages with >60% slug token overlap (Jaccard similarity on slug words split by -):
- Report pairs for review
- For confirmed duplicates: auto-merge into one page, update all backlinks, add redirect note to absorbed page
3. Confidence Upgrade
Pages with 3+ independent sources in frontmatter get upgraded:
low→medium(if 2+ sources)medium→high(if 3+ corroborating sources)- Run
fact-checkeragent on high-confidence pages to verify claims against external sources - Write the reason in log.md
4. Stale Detection (Freshness Tiers)
Pages are evaluated against an intelligent freshness system — not a flat threshold. Each page has a TTL based on its content type:
| Tier | TTL | Examples |
|---|---|---|
live |
15 min | stock prices, live scores, server status, deployment state |
breaking |
1-6 hours | breaking news, incident updates, release announcements |
current |
1-3 days | news articles, current events, trending topics |
fast |
1-4 weeks | AI/LLM/MCP, API changes, model benchmarks |
moderate |
1-3 months | software versions, frameworks, libraries, tools |
standard |
6 months | general knowledge, how-to guides (default) |
academic |
1 year | research papers, studies, formal publications |
evergreen |
5 years | history, biographies, foundational concepts, laws, theorems |
permanent |
never | personal notes, ideas, memories, journal entries |
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.
- 6d ago First seen · 86 lines · 61 tokens per session scan A e9fb4d1e8a1b
wiki-maintain is a skill published in the GitHub repository Oshayr/LLM-Wiki (49 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 900 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 2026-08-30.
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…
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.
slides-polish
Per-page Codex review + targeted python-pptx / Beamer fixes for academic talk slides. Use AFTER /paper-slides (or any externally generated PPTX/Beamer) when the deck looks 'mostly OK' but the user wants a final pass that aligns visual weight with a reference, bumps PPTX fonts to projector-readable size, kills italic…
research-wiki
Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wiki pattern. Use when user says "知识库", "research wiki", "add paper", "wiki query", "查知识库", or wants to build/query a persistent field map.
specification-writing
Write the full patent specification from claims and invention disclosure. Use when user says "撰写说明书", "write specification", "写说明书", "patent description", or wants to draft the complete patent specification.