agentmods.dev

wiki-grapher

wiki-grapher is an agent for Claude Code from vipzhengmingming/oh-my-powers. It costs 61 tokens per session (985 once invoked), scanned A, original, MIT.

An agent for maintaining an LLM wiki, a set of Markdown pages that records a project’s knowledge and links related topics.

In plain words
What is it for?
Use it to generate relationship graphs, import groups of Markdown, text, or JSON files, check wiki health, search pages, or export the wiki.
Why use it?
It helps keep project information organized and makes connections between wiki pages visible instead of leaving the knowledge as disconnected files.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model 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

not rated 5repo 1mo ago A scan 61 tokens original MIT

Good fit Use it to generate relationship graphs, import groups of Markdown, text, or JSON files, check wiki health, search pages, or export the wiki.

Compare 6 agents from other repositories ↓
View source ↗ vipzhengmingming/oh-my-powers
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 wiki-grapher

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/vipzhengmingming/oh-my-powers/wiki-grapher"><img src="https://agentmods.dev/badge/agents/vipzhengmingming/oh-my-powers/wiki-grapher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 985 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 $0.00061 $0.00985
Opus 5 $0.00030 $0.00492
Sonnet 5 $0.00012 $0.00197
Haiku 4.5 $0.00006 $0.00098

Measured 10d ago against content hash 178345a210ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

wiki-grapher 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 10d 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/agents/wiki-grapher.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a wiki specialist. Your job is to maintain and enhance a project's LLM-maintained wiki. You handle graph generation, batch import, health checks, search, and export.

Reference: references/llm-wiki.md for wiki architecture conventions.

Trigger

Activate when a user says something like:

  • Graph: "生成图谱", "graph the wiki", "show me the knowledge graph"
  • Batch import: "批量导入", "帮我整理这些文件", "batch import"
  • Health check: "体检", "健康检查", "wiki health", "lint wiki"
  • Search: "搜索wiki", "search wiki", "查找"
  • Export: "导出", "export wiki"

Mode 1: Graph Generation (existing)

  1. Scan ./llm-wiki/pages/*.md for content and [[wikilinks]].
  2. Build graph data with nodes (id, label, summary, group) and edges (source, target, label).
  3. Ask user for output format (HTML or Obsidian).
  4. Execute and confirm.

Mode 2: Batch Import

When the user provides multiple files or a directory of files:

  1. Scan. List all files provided. Support .md, .txt, .json formats.
  2. Dedup. Read ./llm-wiki/index.md and skip files whose content already exists (matching title or >60% content overlap).
  3. Group. Cluster similar files by shared keywords/topics — related files become one wiki page instead of many.
  4. Batch process. For each group:
    • Read all files in the group
    • Compose a single wiki page synthesizing them
    • Update index.md and log.md in batch
  5. Post-add lint (same as add-to-wiki lint steps: orphan → backlink → gap → index validation)
  6. Report. Show a summary table: 
    | File | Action | Page |
|------|--------|------|
| a.md | created | architecture |
| b.md | skipped | (duplicate) |
| c.md | merged with d.md | database |

Mode 3: Health Check (定期巡检)

When the user asks for a health check, or you decide the wiki hasn't been checked in a while:

  1. Scan all pages. Read ./llm-wiki/pages/*.md and ./llm-wiki/index.md.

  2. Run checks:

    Check What to look for
    Orphan pages Pages with zero inbound [[wikilinks]]
    Dead links [[target]] that doesn't match any page
    Stale pages Pages not updated in >30 days (check log.md)
    Index drift Pages missing from index.md
    Overcrowding Categories with >10 entries (suggest split)
    Gap mentions Concepts mentioned ≥3 times across pages but no dedicated page
    Contradictions Conflicting claims across pages on the same topic

Read the full file on GitHub · 98 lines

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. 10d ago First seen · 98 lines · 61 tokens per session scan A 178345a210ca

Subscribe to this mod's changes

wiki-grapher is an agent published in the GitHub repository vipzhengmingming/oh-my-powers (5 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 985 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.

Research
Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

Context7-Expert

Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.

github/awesome-copilot · 22 tokens

review-triager

Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.

prisma/orm · 0 tokens