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.
npx agentmods add instructions/papadanku/cshade/agents-mdgit clone --depth 1 https://github.com/papadanku/CShadeWrote 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.
[](https://agentmods.dev/instructions/papadanku/cshade/agents-md)<a href="https://agentmods.dev/instructions/papadanku/cshade/agents-md"><img src="https://agentmods.dev/badge/instructions/papadanku/cshade/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00375 | $0.00375 |
| Opus 5 | $0.00187 | $0.00187 |
| Sonnet 5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
CShade AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
CShade Agent Instructions
Repo Type
ReShade HLSL shader collection. No build system, no tests. Only .fx (shaders) and .fxh (headers) files.
Structure
shaders/— Individual shader files (.fx)shaders/shared/— Reusable header files (.fxh) included via#include- Root
README.md— Authoritative source for coding conventions and UI markers
File Types
.fx— Complete ReShade shaders.fxh— HLSL header files for shared code
Coding Conventions (from README.md)
- UI labels/categories: Use
/for subcategories (e.g.,ui_category = "Bloom / Level Weights") - Naming:
- ALLCAPS: state parameters, system semantics
- ALL_CAPS: preprocessor definitions and macros
- _SnakeCase: uniform variables
- SnakeCase: function args, global variables, local variables, textures, samplers
- SNAKE_Case: structs, VertexShader, PixelShader
Shader System
- Core utilities in
shaders/shared/cShade.fxh - Includes composite system, lens effects, blending
- Shaders include cShade.fxh with preprocessor defines to control features
- UI markers:
[D]Depth Buffer,[&]Linked,[+]Preprocessor,[!]Caution,[?]Info,[$]Expensive
Commands
None. This is a shader-only repo. No build, test, or lint steps.
Verification
- Validate HLSL syntax by loading in ReShade
- Check includes resolve correctly
- Verify UI markers match shader capabilities
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.
- 4d ago First seen · 37 lines · 375 tokens per session scan A 8f0d52c4c736
CShade AGENTS.md is an instructions file published in the GitHub repository papadanku/CShade (60 stars, last pushed 12d ago), licensed BSD-3-Clause. It adds 375 tokens to every session, about $0.0019 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.
Other instructions, from other repositories
GameDesignOS AGENTS.md
Instructions for DY-2026/GameDesignOS, covering gamedesignos agent 入口, 默认接法, agent 执行规则, 什么时候用整个项目 and 每个 skill 单独怎么用.
claudemon CLAUDE.md
Instructions for zamarrowski/claudemon, covering ai agent guidelines, project shape, general guidelines, general rules and guards & defensive code.
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.
nes-php-glfw copilot-instructions.md
Instructions for oliverearl/nes-php-glfw, covering github copilot development guidelines for nes emulator, agent document source of truth, project overview, code style & standards and documentation.
game-and-watch-retro-go-sd CLAUDE.md
Claude Code instructions for sylverb/game-and-watch-retro-go-sd, covering claude.md, what this project is, build / flash workflow, architecture and three storage tiers, one elf.
Cities2-MCP AGENTS.md
Instructions for mayor-modder/Cities2-MCP, covering agent rules, workspace safety, commit and pr safety, public-facing writing and merge and release gates.