agentmods.dev

deepwiki

deepwiki is a skill for Claude Code from EntityProcess/allagents. It costs 10 tokens per session (256 once invoked), scanned A, original, MIT.

An AI-generated documentation guide for public GitHub repositories. GitHub is a service where developers host and collaborate on code.

In plain words
What is it for?
Use it to explore a repository’s structure, understand its architecture, ask how a feature works, or compare public repositories.
Why use it?
It gives an overview of an unfamiliar repository without requiring you to inspect every file first, though its documentation may miss recent changes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the deepwiki plugin — 1 skill, 1 MCP server shipped together

not rated 11repo 1mo ago A scan 10 tokens original MIT

Good fit Use it to explore a repository’s structure, understand its architecture, ask how a feature works, or compare public repositories.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/entityprocess/allagents/deepwiki
View source ↗ EntityProcess/allagents allagents.dev
Install

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.

Any agent
npx skills add EntityProcess/allagents --skill deepwiki
Clone the repo
git clone --depth 1 https://github.com/EntityProcess/allagents

Made for: Claude Code.

Or install deepwiki, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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 deepwiki

README.md
[![agentmods](https://agentmods.dev/badge/skills/entityprocess/allagents/deepwiki/github.svg)](https://agentmods.dev/skills/entityprocess/allagents/deepwiki)
Your own site
<a href="https://agentmods.dev/skills/entityprocess/allagents/deepwiki"><img src="https://agentmods.dev/badge/skills/entityprocess/allagents/deepwiki/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 deepwiki

Your own site · 80×15
<a href="https://agentmods.dev/skills/entityprocess/allagents/deepwiki"><img src="https://agentmods.dev/badge/skills/entityprocess/allagents/deepwiki.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 256 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 $0.00010 $0.00256
Opus 5.5 $0.00004 $0.00102
Sonnet 5.5 $0.00002 $0.00051
Haiku 4.5 $0.00001 $0.00026

Measured 2mo ago against content hash 2b06083e1bd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

deepwiki 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 2mo 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/deepwiki/skills/deepwiki/SKILL.md · 30 lines

What it actually says

DeepWiki MCP Tools

When to Use

  • Understanding a GitHub repository's architecture
  • Cross-repo comparisons and Q&A
  • Finding how a specific feature is implemented in a repo
  • Getting an overview of unfamiliar codebases

Available Tools

  • mcp__deepwiki__read_wiki_structure — Get documentation topics for a repo
  • mcp__deepwiki__read_wiki_contents — Read full documentation for a repo
  • mcp__deepwiki__ask_question — Ask any question about a repo

Query Strategies

  • Start with read_wiki_structure to understand what documentation is available
  • Use ask_question for specific implementation questions: "How does auth work in owner/repo?"
  • For comparisons, ask about each repo separately then synthesize
  • Repository names use owner/repo format (e.g., "langchain-ai/langchainjs")

Limitations

  • Free to use, no API key required
  • Only works with public GitHub repositories
  • Documentation is AI-generated and may miss recent changes
  • Best for architecture-level understanding, not line-by-line code review
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. 2mo ago First seen · 30 lines · 10 tokens per session scan A 2b06083e1bd1

Subscribe to this mod's changes

deepwiki is a skill published in the GitHub repository EntityProcess/allagents (11 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 256 once invoked, about $0.0000 per session on Opus 5.5. 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.

ResearchWriting and docsagent-pluginsagent-skills
Related

deepwiki compared with skills from other repositories

deepwiki next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
deepwikiEntityProcess/allagentsSkill111mo agoMITA10Claude Code
document-serviceawslabs/agent-pluginsSkill939todayApache-2.0A141Claude Code
hyperpod-version-checkerawslabs/agent-pluginsSkill939todayApache-2.0A120Claude Code
directory-managementawslabs/agent-pluginsSkill939todayApache-2.0A62Claude Code
dsqlawslabs/agent-pluginsSkill939todayApache-2.0A246Claude Code
ov-experience-memoryvolcengine/OpenVikingSkill42ktodayAGPL-3.0A78Claude Code, Codex
finetuningawslabs/agent-pluginsSkill939todayApache-2.0A85Claude Code