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 jscraik/Agent-Skills --skill llm-wikigit clone --depth 1 https://github.com/jscraik/Agent-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/jscraik/agent-skills/llm-wiki)<a href="https://agentmods.dev/skills/jscraik/agent-skills/llm-wiki"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/llm-wiki/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/jscraik/agent-skills/llm-wiki"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/llm-wiki.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.01125 |
| Opus 5 | $0.00026 | $0.00562 |
| Sonnet 5 | $0.00010 | $0.00225 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
llm-wiki 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 9d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Wiki
Philosophy
Cited local files beat remembered answers.
When To Use
Use when durable local markdown should change.
Anti-Patterns
Avoid one-off answers, uncited summaries, and broad vault reorganization.
Inputs
Confirm domain, vault/workspace path, raw-source path, source sensitivity (public, internal, confidential, or restricted), workflow (ingest, query, lint, or repair), citation style, attachment path, and whether reusable answers should be filed back into the wiki.
Discovery Interview
Ask one round at a time: one plain-language question plus Why this matters:; avoid dumping the full interview plan at once.
Constraints
Redact sensitive content by default. Keep raw sources read-only. Preserve citations.
Execution Boundaries
Write only approved pages, indexes, logs, schemas, governance files, or narrow helpers. Require explicit approval for private attachments, network retrieval, sync/sharing, publishing, vector infrastructure, bulk renames, merges, or reorganization.
Workflows
Ingest: classify each source, read one source or bounded batch, extract path/page/heading evidence, create or update source summaries, update affected concept/entity/synthesis pages, strengthen wikilinks, then update index and log.
Query: start with index/log and linked pages, read raw sources only when needed, answer with citations, mark uncertainty, and file reusable synthesis back into the wiki when it will compound.
Lint: check contradictions, stale claims, orphan pages, missing concepts, weak links, duplicate aliases, unsupported assertions, brittle attachments, and data gaps. Formal sweeps return schema_version: lint-report/v1 with severity, evidence, status, and owner.
Concrete Output Shapes
Use these compact patterns: index rows - [[concepts/local-first-knowledge]] - claim area; source summaries with optional frontmatter type, status, sources, aliases, confidence, reviewed, and supersedes; citations like [raw/articles/source.pdf#p4]; log rows like 2026-05-24: added [[sources/x]], updated [[concepts/y]], no bulk renames.
What ships with it
7 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.
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.
- 9d ago First seen · 88 lines · 51 tokens per session scan A bffabfa95f4b
llm-wiki is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 11d ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,125 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 2026-09-03.
Other skills, from other repositories
humanizer-zh
Revise Chinese text to sound specific, fluent, restrained, and human while preserving facts and author intent.
skill-creator
Design and write concise reusable KunAgent skills with valid triggers, real tools, and testable completion criteria.
ad-creative
Plan and produce advertising concepts, copy variants, visual directions, and test matrices for paid campaigns.
daily-brief
Produce a dated, source-linked daily brief with prioritized developments, implications, and watch items.
imf-data
Retrieve and analyze IMF macroeconomic series, forecasts, and reserve-composition data.
scholar-research
Search, screen, synthesize, and cite scholarly literature and author metadata.