renderdoc-skill CLAUDE.md

A Claude Code instruction file for connecting RenderDoc, a graphics debugging tool, with an application through its command-line interface.

In plain words
What is it for?
It guides GPU debugging for Vulkan, Direct3D, and OpenGL applications, including frame capture and exporting images, meshes, and buffers for analysis.
Why use it?
It records the environment settings, capture locations, and application details needed to inspect GPU frames correctly.

Instructions file

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.

agentmods
npx agentmods add instructions/rudybear/renderdoc-skill/claude-md
Clone the repo
git clone --depth 1 https://github.com/rudybear/renderdoc-skill
Per session 464 This file is loaded in full into every session.
When invoked 464 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00464 $0.00464
Opus 5 $0.00232 $0.00232
Sonnet 5 $0.00093 $0.00093
Haiku 4.5 $0.00046 $0.00046

Measured 3d ago against content hash 136040b3eb7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

renderdoc-skill CLAUDE.md 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 3d 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.

CLAUDE.md · 52 lines

What it actually says

RenderDoc + Claude Code GPU Debugging

Project Overview

This project wires Claude Code to RenderDoc via rdc-cli, enabling automated GPU frame capture, inspection, and debugging for Vulkan/D3D/GL applications.

Tools

  • rdc-cli (rdc): 66-command CLI wrapping RenderDoc's Python API. Installed via pip install rdc-cli.
  • renderdoc.pyd: Python module from RenderDoc (built from source or from an official install).

Environment

  • RENDERDOC_PYTHON_PATH=<path-to-renderdoc-module> — rdc-cli uses this to find renderdoc.pyd
  • Captures go in ./captures/ (or any directory you choose)
  • Analysis exports (PNGs, meshes, buffers) go in ./captures/analysis/

Your Application (customize this section)

  • Executable: /path/to/your/app
  • CWD requirement: Set CWD to your project root if the app resolves assets relative to CWD
  • Debug markers: List any debug markers your app emits (e.g., "Shadow Pass", "GBuffer Pass")
  • Scenes / modes: List any flags or scenes relevant to your app

Capture Requirements

  • Vulkan layer: Must be registered (see README.md for setup)
  • Environment: ENABLE_VULKAN_RENDERDOC_CAPTURE=1 must be set for Vulkan apps
  • Swapchain: The app must present frames (headless apps without vkQueuePresentKHR cannot be captured)
  • Capture script: See capture_frame.py for an example using the RenderDoc Python API directly

Quick Start

# Check setup
rdc doctor

# Capture a frame (adapt the capture script for your app)
python capture_frame.py

# Inspect
rdc open ./captures/my_capture.rdc
rdc info --json
rdc draws --limit 20
rdc close

GPU Debugging Skill

See .claude/skills/renderdoc-gpu-debug/SKILL.md for the full GPU debugging skill with workflows, recipes, and command reference.

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. 3d ago First seen · 52 lines · 464 tokens per session scan A 136040b3eb7d

Subscribe to this mod's changes

renderdoc-skill CLAUDE.md is an instructions file published in the GitHub repository rudybear/renderdoc-skill (202 stars, last pushed 6mo ago), licensed MIT. It adds 464 tokens to every session, about $0.0023 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens