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/ackeskin/contexture/renderinggit clone --depth 1 https://github.com/AcKeskin/contextureWhat 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 | $0.03515 | $0.03515 |
| Opus 5 | $0.01758 | $0.01758 |
| Sonnet 5 | $0.00703 | $0.00703 |
| Haiku 4.5 | $0.00351 | $0.00351 |
Grade A, and why
contexture rendering.instructions.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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rendering rules
Auto-loaded by Copilot when editing files matching
**. Generated fromarchitectural-rules/rendering/— do not hand-edit.
Color Space and Precision Discipline
All lighting and shading calculations must be performed in linear light (scene-linear color space); sample sRGB textures through hardware linearization (GL_SRGB8_ALPHA8 / DXGI_FORMAT_*_SRGB / MTLPixelFormatRGBA8Unorm_sRGB) so the hardware converts on read. Mixing gamma-encoded values with linear math produces physically incorrect results. (IEC 61966-2-1 sRGB standard; OpenGL 4.6 spec §8.24 "sRGB Conversion"; Khronos data format spec)
Apply the linear-to-sRGB (or target OETF) conversion exactly once, at the final swapchain/output boundary — via sRGB framebuffer attachment (GL_FRAMEBUFFER_SRGB / DXGI_FORMAT_*_SRGB swapchain), post-process tone-map output, or explicit gamma encode in the final fragment. Do not gamma-encode intermediate render targets. (OpenGL 4.6 spec §17.3.9; D3D11/D3D12 DXGI swap chain format guidelines)
For HDR output paths, apply the correct OETF for the target display standard (PQ/ST.2084 for HDR10, HLG for broadcast) in the tone-mapping pass, not ad-hoc gamma curves. HDR10 metadata (MaxCLL, MaxFALL) must be set correctly; incorrect OETF yields washed-out or clipped images on HDR displays. (ITU-R BT.2100 HDR standard; SMPTE ST.2084 PQ EOTF; D3D12 HDR output guide; Vulkan VK_EXT_hdr_metadata)
Use float16 (R16G16B16A16_FLOAT / GL_RGBA16F) or higher for HDR intermediate render targets; R8G8B8A8_UNORM is insufficient for HDR accumulation or lighting buffers and causes precision loss and banding. Use R11G11B10_FLOAT for HDR when alpha is not needed to save bandwidth. (general HDR render target best practice; GPU Pro / GPU Gems references)
Do not accumulate (additive blend, multipass light accumulation) into 8-bit unorm render targets; the quantization error compounds per pass and produces visible banding. Accumulate in float16 or higher, then resolve/tonemap to 8-bit at output. (general rendering precision best practice; physically based rendering literature)
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.
- yesterday First seen · 100 lines · 3,515 tokens per session scan A c40a73ad82f4
contexture rendering.instructions.md is an instructions file published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 3,515 tokens to every session, about $0.0176 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 2026-08-31.
Other instructions, from other repositories
agentic-workflow CLAUDE.md
Instructions for gtrabanco/agentic-workflow, covering claude.md, repository layout, working rules, authoring a skill and hand off, don't compose across a model/effort boundary.
ccjk AGENTS.md
Instructions for miounet11/ccjk, covering repository guidelines, source of truth, behavior, validation and notes.
ccjk CLAUDE.md
Instructions for miounet11/ccjk: 持久知识唯一来源：docs/CLAUDE-NOTES.md（请优先阅读本文档）.
stenographer-mode copilot-instructions.md
Instructions for AkashAi7/stenographer-mode, covering steno mode — global instructions, contract, rules and levels.
context-engineering AGENTS.md
Instructions for fending/context-engineering, covering agents.md, what this project is, structure, standards and navigation.
capy CLAUDE.md
Claude Code instructions for serpro69/capy, covering claude.md, project, architecture, key packages and critical invariants.