Driver Analysis

Driver Analysis is a skill for Claude Code, Codex from buzzer-re/Rikugan. It costs 20 tokens per session (509 once invoked), scanned A, original, MIT.

A guide for examining Windows kernel drivers, which are programs that run at the core of Windows and interact directly with hardware and system services. It focuses on startup code, request handlers, and control codes used by applications to communicate with the driver.

In plain words
What is it for?
Use it to trace driver startup, map request handlers, document IOCTL operations, inspect data structures, and look for kernel memory access or process-token manipulation.
Why use it?
It gives a structured way to understand what a driver does and spot unsafe behavior without reading every part of the binary at once.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to trace driver startup, map request handlers, document IOCTL operations, inspect data structures, and look for kernel memory access or process-token manipulation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/buzzer-re/rikugan/driver-analysis
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 buzzer-re/Rikugan --skill driver-analysis
Clone the repo
git clone --depth 1 https://github.com/buzzer-re/Rikugan

Made for: Claude Code, Codex.

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 Driver Analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/buzzer-re/rikugan/driver-analysis/github.svg)](https://agentmods.dev/skills/buzzer-re/rikugan/driver-analysis)
Your own site
<a href="https://agentmods.dev/skills/buzzer-re/rikugan/driver-analysis"><img src="https://agentmods.dev/badge/skills/buzzer-re/rikugan/driver-analysis/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 Driver Analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/buzzer-re/rikugan/driver-analysis"><img src="https://agentmods.dev/badge/skills/buzzer-re/rikugan/driver-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 509 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00020 $0.00509
Opus 5.5 $0.00008 $0.00204
Sonnet 5.5 $0.00004 $0.00102
Haiku 4.5 $0.00002 $0.00051

Measured 1mo ago against content hash 26222ca41d9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Driver Analysis 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 1mo 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.

rikugan/skills/builtins/driver-analysis/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task: Windows Kernel Driver Analysis. You are analyzing a kernel-mode driver binary.

Mandatory First Steps

  1. Find DriverEntry — usually the binary entry point
    • Signature: NTSTATUS DriverEntry(DRIVER_OBJECT*, UNICODE_STRING*)
    • Use decompile_function on the entry point
  2. From DriverEntry, extract:
    • MajorFunction dispatch table assignments
    • DriverUnload pointer
    • DeviceName and SymbolicLinkName
  3. Identify IOCTL handlers — look for IRP_MJ_DEVICE_CONTROL dispatch entry

Key Data Structures

Use create_struct and set_type early — these appear in virtually every driver:

  • DRIVER_OBJECT, DEVICE_OBJECT
  • IRP, IO_STACK_LOCATION
  • UNICODE_STRING

Apply types with set_function_prototype and apply_type_to_variable to make decompiled code readable immediately.

IOCTL Analysis

For each IRP_MJ_DEVICE_CONTROL handler:

  1. decompile_function on the dispatch function
  2. Find the switch statement on IoControlCode
  3. For each IOCTL code, document:
    • IOCTL value and decoded method/access
    • Expected input/output buffer sizes
    • Operation performed
  4. Check for dangerous patterns:
    • Kernel memory read/write gadgets
    • Process token manipulation
    • Arbitrary code execution paths

Common Vulnerabilities to Flag

  • KeSetEvent with user-controlled address — kernel write primitive
  • Missing ProbeForRead/ProbeForWrite before kernel-mode buffer copy
  • Unchecked buffer sizes in METHOD_NEITHER IOCTLs — pool overflow
  • MmMapIoSpace with user-supplied physical address — arbitrary physical memory access
  • Direct stack buffer reads without size validation — kernel stack overflow
  • ObReferenceObjectByHandle without proper access checks

Analysis Workflow

  1. Map the dispatch table → understand all supported IRPs
  2. Deep-dive each IOCTL handler → document input/output
  3. Trace data flow from usermode input to kernel operations
  4. Flag every path where user-controlled data reaches a sensitive kernel API
  5. Rename functions as you understand them: DispatchDeviceControl, HandleIoctlReadPhysMem, etc.

Read the full file on GitHub · 58 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. 1mo ago First seen · 58 lines · 20 tokens per session scan A 26222ca41d9b

Subscribe to this mod's changes

Driver Analysis is a skill published in the GitHub repository buzzer-re/Rikugan (690 stars, last pushed 8d ago), licensed MIT. It adds 20 tokens to every session and 509 once invoked, about $0.0001 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.

Related

Other skills, from other repositories