graph-wiki

graph-wiki is a skill for Claude Code from vipzhengmingming/oh-my-powers. It costs 59 tokens per session (462 once invoked), scanned A, original, MIT.

A tool that turns an LLM wiki—a project knowledge base written in Markdown—into a visual map of related pages.

In plain words
What is it for?
It creates an interactive HTML graph or adds links for viewing in Obsidian, a Markdown note-taking app. It requires an existing project wiki.
Why use it?
It makes links and inferred connections between project topics easier to see than reading pages one by one.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the create-llm-wiki plugin — 5 skills, 1 agent shipped together

Good fit It creates an interactive HTML graph or adds links for viewing in Obsidian, a Markdown note-taking app. It requires an existing project wiki.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add vipzhengmingming/oh-my-powers
Claude Code
/plugin install create-llm-wiki

Made for: Claude Code.

Or install create-llm-wiki, the plugin that ships this one along with the rest of its 5 skills, 1 agent.

Wrote 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.

agentmods badge for graph-wiki

README.md
[![agentmods](https://agentmods.dev/badge/skills/vipzhengmingming/oh-my-powers/graph-wiki/github.svg)](https://agentmods.dev/skills/vipzhengmingming/oh-my-powers/graph-wiki)
Your own site
<a href="https://agentmods.dev/skills/vipzhengmingming/oh-my-powers/graph-wiki"><img src="https://agentmods.dev/badge/skills/vipzhengmingming/oh-my-powers/graph-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.

agentmods 80×15 button for graph-wiki

Your own site · 80×15
<a href="https://agentmods.dev/skills/vipzhengmingming/oh-my-powers/graph-wiki"><img src="https://agentmods.dev/badge/skills/vipzhengmingming/oh-my-powers/graph-wiki.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 462 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.00462
Opus 5 $0.00030 $0.00231
Sonnet 5 $0.00012 $0.00092
Haiku 4.5 $0.00006 $0.00046

Measured 9d ago against content hash 11ebf7461757, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

graph-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.

plugins/create-llm-wiki/skills/graph-wiki/SKILL.md · 41 lines

What it actually says

Graph Wiki

Generate a visual relationship graph from the project's LLM wiki.

Reference: references/llm-wiki.md for wiki architecture conventions.
Agent: the wiki-grapher agent handles the actual analysis and generation — this skill coordinates the flow.

Steps

  1. Read references/llm-wiki.md to understand wiki conventions.

  2. Check that the wiki exists (./llm-wiki/index.md). If not, suggest the user run /create-llm-wiki:init-wiki first.

  3. Scan ./llm-wiki/pages/*.md for content and [[wikilinks]]. Build a graph data structure:

    • Nodes: each wiki page → { id, label, summary, group }
    • Edges: each [[wikilink]]{ source, target, label }. Also infer implicit relationships from shared keywords.
  4. Ask user for output format (or use the argument if provided):

    • html — Generate interactive D3.js graph. Pipe JSON to ${CLAUDE_PLUGIN_ROOT}/scripts/graph-viz.js, write output to ./llm-wiki/graph.html. Tell user to open it in a browser.
    • obsidian — Add/update [[wikilinks]] in page files. Tell user to open Obsidian and use Graph View.
  5. Execute based on user's choice.

  6. Confirm where the output was generated and how to view it.

Important Notes

  • Check existing [[wikilinks]] first — don't duplicate.
  • For implicit relationships, add a label explaining the connection.
  • ${CLAUDE_PLUGIN_ROOT} expands to the plugin root in shell commands — pass it as-is.
  • The graph-viz.js script reads JSON from stdin and writes HTML to stdout.
Changes

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.

  1. 9d ago First seen · 41 lines · 59 tokens per session scan A 11ebf7461757

Subscribe to this mod's changes

graph-wiki is a skill published in the GitHub repository vipzhengmingming/oh-my-powers (5 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 462 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens