renderdoc-analyzer

renderdoc-analyzer is a skill for Claude Code, Codex from Hengle/RenderDocMCP2. It costs 149 tokens per session (2,506 once invoked), scanned A, original, MIT.

A skill for examining RenderDoc capture files and tracing how a selected part of a rendered frame was produced. RenderDoc is a graphics debugging tool, and an RDC file is a saved frame capture.

In plain words
What is it for?
Use it to inspect specified draw calls, reverse-engineer vertex and pixel shaders, examine texture and buffer data, export graphics assets, and document the rendering process.
Why use it?
It provides evidence-based inspection of draw calls, shaders, textures, and rendering costs instead of relying only on the final picture or assumptions.

Skill for Claude CodeCodex

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

Good fit Use it to inspect specified draw calls, reverse-engineer vertex and pixel shaders, examine texture and buffer data, export graphics assets, and document the rendering process.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hengle/renderdocmcp2/renderdoc-skill
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 Hengle/RenderDocMCP2 --skill renderdoc-skill
Clone the repo
git clone --depth 1 https://github.com/Hengle/RenderDocMCP2

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 renderdoc-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/skills/hengle/renderdocmcp2/renderdoc-skill/github.svg)](https://agentmods.dev/skills/hengle/renderdocmcp2/renderdoc-skill)
Your own site
<a href="https://agentmods.dev/skills/hengle/renderdocmcp2/renderdoc-skill"><img src="https://agentmods.dev/badge/skills/hengle/renderdocmcp2/renderdoc-skill/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 renderdoc-analyzer

Your own site · 80×15
<a href="https://agentmods.dev/skills/hengle/renderdocmcp2/renderdoc-skill"><img src="https://agentmods.dev/badge/skills/hengle/renderdocmcp2/renderdoc-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 149 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,506 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 $0.00149 $0.02506
Opus 5.5 $0.00060 $0.01002
Sonnet 5.5 $0.00030 $0.00501
Haiku 4.5 $0.00015 $0.00251

Measured 1mo ago against content hash 3b304be5d76c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

renderdoc-analyzer 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.

renderdoc-Skill/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RenderDoc 抓帧逆向分析

概述

此 Skill 提供从 RenderDoc 抓帧文件(.rdc)进行渲染逆向工程的完整工作流,涵盖:

  • 打开并浏览 .rdc 抓帧文件
  • 识别和定位特定渲染部件的 DrawCall
  • 逆向分析着色器(顶点 + 片元)
  • 导出贴图、模型、Shader 为 Unity 可用资产
  • 生成渲染耗时统计和完整使用文档

核心原则

⚠️ 人工决策优先

严禁自行决定分析范围。 必须由用户明确指定要分析的部件或范围:

  • 如果用户说"分析头发"→ 只分析头发相关 DrawCall
  • 如果用户说"分析全部"→ 分析所有 DrawCall
  • 如果用户说"分析这个 DrawCall"→ 只分析指定的 Event ID
  • 如果用户没有指定分析范围 → 主动询问用户要分析哪些部件,提供 DrawCall 列表供选择

⚠️ 基于证据判断

严禁凭经验猜测。 所有判断必须基于实际数据:

  • 识别 DrawCall 内容必须通过缩略图对比,不能仅凭面数猜测
  • Shader 逆向必须基于 SPIR-V/DXBC 反编译,不能凭渲染效果推测算法
  • CBuffer 参数必须从反射数据精确提取 byte offset,不能假设布局
  • 纹理用途必须通过查看实际贴图内容确认,不能仅凭 slot 名猜测

工作流

整个分析流程分为 6 个阶段。根据用户需求执行部分或全部阶段。

阶段 1:打开抓帧

  1. 检查 RenderDoc 是否在运行(ping)
  2. 如未运行,使用 launch_renderdoc 启动并加载 .rdc 文件
  3. 如已运行,使用 open_capture 打开指定文件
  4. 等待 bridge 就绪(大文件可能需要 60-90 秒)
  5. 使用 get_capture_status 确认 API 类型(Vulkan/D3D11/D3D12/OpenGL)

阶段 2:帧概览与 DrawCall 识别

  1. get_frame_summary 获取帧统计(总 DrawCall 数、Dispatch 数等)
  2. get_draw_calls 获取渲染层级结构,识别主要 Render Pass
  3. identify_drawcalls 生成每个 DrawCall 的 RT 缩略图:
    • 指定 output_dir 保存缩略图 PNG
    • 指定 render_target 为主色彩 RT 的资源 ID
    • 限定 event_id_min/event_id_max 到主渲染 Pass 范围
  4. 查看缩略图逐一比对,精确识别每个 DrawCall 渲染的内容(皮肤、头发、眼睛、装备等)
  5. 将识别结果汇报给用户,等待用户指定要深入分析的部件

阶段 3:Shader 逆向分析

对用户指定的目标 DrawCall:

  1. reverse_shader 获取片元着色器完整数据:
    • SPIR-V/DXBC 反编译
    • CBuffer 反射数据(精确 byte offset)
    • 绑定纹理列表(资源 ID、尺寸、推断角色)
    • 运行时 CBuffer 值
  2. reverse_shader 获取顶点着色器数据
  3. get_pipeline_state 获取完整管线状态(RT 格式、Viewport、混合模式、深度测试等)
  4. get_bound_textures 确认纹理绑定的实际资源 ID
  5. export_drawcall 导出完整 DrawCall 数据(所有平台反汇编 + 纹理 PNG + summary.json)
  6. 查看导出的纹理图片确认每张贴图的实际内容和用途

逆向代码时的精确性要求(详见 references/workflow.md):

  • 所有 helper 函数必须 1:1 从 SPIR-V/DXBC 指令翻译
  • 所有魔法数字必须从常量池精确提取,注释来源
  • CBuffer 布局必须精确到 byte offset
  • 循环结构必须从控制流精确还原

阶段 4:Unity 资产导出

当用户要求导出到 Unity 时:

  1. 创建输出目录结构:
    <OutputName>/
    ├── <Name>.shader        # Unity ShaderLab + HLSL
    ├── Textures/            # 所有关联纹理
    └── Models/              # 网格模型 (.fbx/.obj)
    

Read the full file on GitHub · 180 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 180 lines · 149 tokens per session scan A 3b304be5d76c

Subscribe to this mod's changes

renderdoc-analyzer is a skill published in the GitHub repository Hengle/RenderDocMCP2 (36 stars, last pushed 6mo ago), licensed MIT. It adds 149 tokens to every session and 2,506 once invoked, about $0.0006 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