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/jackwener/llm-wiki/querynpx skills add jackwener/llm-wiki --skill querygit clone --depth 1 https://github.com/jackwener/llm-wikiWhat 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 | $0.00043 | $0.00432 |
| Opus 5 | $0.00022 | $0.00216 |
| Sonnet 5 | $0.00009 | $0.00086 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
query 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 3d 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 an LLM Wiki
Answer from the maintained wiki, then capture only durable synthesis that makes future queries more useful.
Workflow
- Find the vault and read
wiki-purpose.md; confirm that the question falls within its intended scope. Readwiki-schema.mdfor local conventions. - Search with
llm-wiki search "<question>". Use--bm25-onlyonly when vector search is unavailable or inappropriate. Scanwiki/for exact terms if needed. - Read the matched pages and follow relevant
[[wikilinks]]and## Relatedsections. Use the graph as context rather than treating search ranking as the answer. - Give a direct answer grounded in the pages. Cite pages as
[[slug]], state uncertainty, distinguish evidence from inference, and surface conflicts or gaps instead of guessing. - If the wiki lacks enough evidence, say so and suggest specific material to ingest. Do not fill gaps from unsaved external knowledge.
When knowledge should compound
Write back only a non-trivial, high-confidence synthesis: for example, a new connection among at least three pages, a resolved contradiction, or a useful comparison absent from all source pages. Do not create a page for a simple lookup or speculative conclusion.
For a durable synthesis, create a focused wiki page with complete frontmatter:
---
title: Synthesis Title
description: One-line summary
tags: [synthesis]
sources: [contributing-page-slugs]
source_type: query-synthesis
created: YYYY-MM-DD
updated: YYYY-MM-DD
---
Link it to the contributing pages, append a query entry to wiki-log.md,
and run llm-wiki sync. Do not modify anything under sources/.
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.
- 3d ago First seen · 50 lines · 43 tokens per session scan A 82508f1badae
query is a skill published in the GitHub repository jackwener/llm-wiki (101 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 432 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…