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/hamsurang/kit/deepwiki-clinpx skills add hamsurang/kit --skill deepwiki-cligit clone --depth 1 https://github.com/hamsurang/kitWhat 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 | $0.00073 | $0.00573 |
| Opus 5 | $0.00036 | $0.00287 |
| Sonnet 5 | $0.00015 | $0.00115 |
| Haiku 4.5 | $0.00007 | $0.00057 |
Grade A, and why
deepwiki-cli 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 2d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
deepwiki-cli Skill
deepwiki-cli provides AI-generated wiki documentation for GitHub repositories.
Use the deepwiki-cli to query it directly — this keeps only the result text
in Claude's context, avoiding MCP protocol overhead.
When This Skill Activates
- User references a GitHub repository by name (owner/repo format)
- User asks how a library or framework works
- User needs to understand a codebase they haven't read locally
- User asks architecture or API questions about an open-source project
How to Use
Run via Bash tool:
# Ask a question about a repository
deepwiki-cli ask <owner/repo> "<question>"
# List wiki topics for a repository
deepwiki-cli structure <owner/repo>
# Read full wiki contents
deepwiki-cli read <owner/repo>
Examples
deepwiki-cli ask facebook/react "How does the reconciler work?"
deepwiki-cli ask vercel/next.js "What is the App Router architecture?"
deepwiki-cli structure rust-lang/rust
deepwiki-cli read tokio-rs/tokio
Prerequisites
The deepwiki-cli binary must be installed:
cargo install deepwiki-cli
If the binary is not found, inform the user to install it first.
When NOT to Use
- Repository is already cloned locally — use Glob/Grep/Read tools directly
- Repository is private — deepwiki-cli only works with public repositories
- User is asking about their own code in the current working directory
Error Handling
If deepwiki-cli is not installed or a command fails:
- Check if the binary exists:
which deepwiki-cli - If not found, tell the user to install:
cargo install deepwiki-cli - If the repository is not found, verify the owner/repo format
- If the command times out, try
deepwiki-cli structurefirst (lighter query), then ask specific questions - As a last resort, fall back to web search for the repository's documentation
Why This Saves Tokens
Using the CLI via Bash outputs only the result text to Claude's context.
Connecting deepwiki-cli as an MCP server adds initialize handshake + tool listing
overhead on every session start.
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.
- 2d ago First seen · 79 lines · 73 tokens per session scan A 0418b4e10c47
deepwiki-cli is a skill published in the GitHub repository hamsurang/kit (19 stars, last pushed 4mo ago), licensed MIT. It adds 73 tokens to every session and 573 once invoked, about $0.0004 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
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…