Skip to content
Get packs

Kernel Analysis for vphone600

Look up symbols and addresses in vphone600 kernel dumps and compare them with XNU source

Source Download skill
Repository
Lakr233/vphone-cli
Stars
16,382
Licence
MIT
Files
3 files

What it does

This skill teaches an AI agent to work on the vphone600 kernel reverse-engineering dataset stored in the repository. Instead of guessing, the agent first queries a local symbol database and JSON symbol files to find function names and addresses in the release and research kernel builds, then checks the matching behaviour in the open-source XNU kernel source. It also asks the agent to clearly separate confirmed facts from its own inferences and to name the exact kernel used.

Great for

  • Reverse engineers studying the vphone600 kernelcache
  • Researchers comparing release and research kernel builds for patch analysis
  • Developers who need to map a raw address to a known kernel symbol

Skip it if

  • Analysing kernels for other devices or Apple platforms, since the skill is limited to vphone600 by design
  • Anyone without the repository's Research/KernelSymbols data, because the skill cannot answer lookups without those files
  • Using the output to change or ship modified kernels without independent verification, as the skill only supports analysis and its findings are labelled as partly inferred

Try asking

  • “Look up the symbol name at address 0xfffffff007004000 in the release vphone600 kernel”
  • “Compare how a given function differs between the release and research vphone600 symbol sets”
  • “Explain what this XNU function does and find where the matching code lives in Research/Reference/xnu”
  • “Find the symbol paths and addresses related to a patch I am analysing for vphone600”
Step-by-step guide: how to use Kernel Analysis for vphone600Install, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 3 original files, the MIT licence and an attribution note.

    kernel-analysis-vphone600.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip kernel-analysis-vphone600.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip kernel-analysis-vphone600.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Point the agent at the repository root so it can find Research/KernelSymbols and resolve JSON paths locally, since stored absolute paths may be wrong.
  • Ask for the kernel name and address in every answer so results are traceable.
  • Clone the XNU reference with --depth 1 as the skill suggests to keep the download small.

What's inside

  • agents/openai.yaml
  • references/kernel-info-queries.md
  • SKILL.md

Redistributed unmodified from Lakr233/vphone-cli under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.