agentmods.dev

searchpo-deepwiki-research

searchpo-deepwiki-research is a skill for Claude Code from SunflowersLwtech/sunkit. It costs 47 tokens per session (731 once invoked), scanned A, original, Apache-2.0.

A research helper for understanding GitHub repositories, their structure, dependencies, and source code, with DeepWiki as an additional documentation source.

In plain words
What is it for?
Exploring repository architecture, tracing dependencies, querying DeepWiki, and adding code context to research.
Why use it?
It provides repository context when a Searchpo task needs more than the initial research evidence.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code; mentions Codex.

Part of the searchpo plugin — 8 skills, 1 command, 3 agents, 1 plugin shipped together

not rated 13repo today A scan 47 tokens original Apache-2.0

Good fit Exploring repository architecture, tracing dependencies, querying DeepWiki, and adding code context to research.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sunflowerslwtech/sunkit/searchpo-deepwiki-research
View source ↗ SunflowersLwtech/sunkit sunflowerslwtech.github.io
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 SunflowersLwtech/sunkit --skill searchpo-deepwiki-research
Clone the repo
git clone --depth 1 https://github.com/SunflowersLwtech/sunkit

Made for: Claude Code.

Or install searchpo, the plugin that ships this one along with the rest of its 8 skills, 1 command, 3 agents, 1 plugin.

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 searchpo-deepwiki-research

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sunflowerslwtech/sunkit/searchpo-deepwiki-research"><img src="https://agentmods.dev/badge/skills/sunflowerslwtech/sunkit/searchpo-deepwiki-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 731 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 $0.00047 $0.00731
Opus 5.5 $0.00019 $0.00292
Sonnet 5.5 $0.00009 $0.00146
Haiku 4.5 $0.00005 $0.00073

Measured 2mo ago against content hash 321c75f577a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

searchpo-deepwiki-research 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/searchpo/.claude/skills/searchpo-deepwiki-research/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Searchpo DeepWiki Research

Use this skill for repo-focused context collection. DeepWiki is a supporting repository-intelligence surface, not a replacement for Searchpo canonical evidence or AnySearch supplemental research.

MCP Setup

  • Project MCP config lives in .mcp.json and declares deepwiki as https://mcp.deepwiki.com/mcp.
  • Codex can use mcp__deepwiki.read_wiki_structure, mcp__deepwiki.read_wiki_contents, and mcp__deepwiki.ask_question when those tools are available.
  • Claude Code tool names are usually mcp__deepwiki__read_wiki_structure, mcp__deepwiki__read_wiki_contents, and mcp__deepwiki__ask_question.
  • Do not call DeepWiki generate_wiki unless the user explicitly asks to generate a wiki.

Workflow

  1. Confirm the input is a GitHub repo URL or owner/repo.
  2. Confirm searchpo-research-agent has started the AnySearch-first evidence path: canonical URL detail, GitHub API/README evidence, and AnySearch search/extract planning. If not, return to searchpo-research-agent first.
  3. Run python3 scripts/agent_capabilities.py --profile repo --format text to verify MCP/key availability without printing secrets.
  4. Use DeepWiki in this order:
    • read_wiki_structure to find topic areas.
    • read_wiki_contents when full repo documentation is useful and concise enough.
    • ask_question for targeted questions such as architecture, CLI entrypoint, render path, API boundary, or safety model.
  5. If DeepWiki reports that the repository is not indexed or not found, record that and continue with GitHub API/README plus AnySearch. Do not block the run only because DeepWiki lacks a wiki.
  6. Cross-check DeepWiki findings against Searchpo evidence requirements:
    • canonical URL detail fetch,
    • GitHub API metadata and README evidence for GitHub repos,
    • at least two independent supplemental AnySearch extracts,
    • fact_bank.json, topic_brief.json, and cross_check_review.json.
  7. Store conclusions only in run-scoped artifacts or final analysis; never write .env values.

Read the full file on GitHub · 56 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. 2mo ago First seen · 56 lines · 47 tokens per session scan A 321c75f577a2

Subscribe to this mod's changes

searchpo-deepwiki-research is a skill published in the GitHub repository SunflowersLwtech/sunkit (13 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 731 once invoked, about $0.0002 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.

Claude CodeFrontendPlanningResearchcognitive-toolsdesign-systemprompt-engineeringtacit-knowledge
Related

Other skills, from other repositories

tidyfactor-styler

Production framework styler and surgical RTL UI polish engine with Contextual Decision Layer (CDL). Operates directly inside existing codebases across React/Next.js, PHP, WordPress, and Vanilla HTML/CSS/JS. Trigger on commands 'brief', 'component', 'section', 'page', 'redesign', 'typography', 'palette', 'layout'…

TidyFactor/Styler · 100 tokens

ui-styles

Participate before building or changing product UI: websites, apps, demos, dashboards, forms, visual redesigns, component-library selection, themes and interaction states. Act as a practical designer: understand the product, recommend and preview a direction, preserve a project visual standard, and implement it using…

chrzamz/ui-styles-skill · 97 tokens

ui-style-creator

A tool for creating and saving a reusable visual style from a product brief, an existing interface, or reference designs. A visual style can include shared choices used across an interface or project.

chrzamz/ui-styles-skill · 62 tokens

lovable-design-system

Distinctive, production-grade frontend design with bold aesthetic direction, curated palette/typography/layout presets, and a structured design-direction flow. Use whenever building or refining UI (landing pages, product surfaces, marketing sites, dashboards) — especially when the brief is visual, broad, or "make it…

Mine77/lovable-design-skills · 0 tokens

material-ui-tailwind

Integrates Material UI with Tailwind CSS v4 using cascade layers (enableCssLayer, @layer order) and documents Tailwind v3 interoperability (preflight, important, injectFirst, portals). Use when combining MUI with Tailwind utilities, slotProps className, or theme token bridges.

mui/material-ui · 67 tokens

fast-typescript-check

Keep www-sacred's TypeScript fast to type-check and fast to run. Use when touching the ASCII/canvas animation components (the only real per-frame code here), tightening type-check wall-clock, or auditing a change for runtime or compiler regressions. Scoped to this repo — a React 19 / Next.js 16 component library plus…

internet-development/www-sacred · 84 tokens