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/dungnotnull/shader-cache-optimization-agent-skill/claude-mdgit clone --depth 1 https://github.com/dungnotnull/shader-cache-optimization-agent-skillWrote 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/dungnotnull/shader-cache-optimization-agent-skill/claude-md)<a href="https://agentmods.dev/instructions/dungnotnull/shader-cache-optimization-agent-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/dungnotnull/shader-cache-optimization-agent-skill/claude-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 | $0.01250 | $0.01250 |
| Opus 5 | $0.00625 | $0.00625 |
| Sonnet 5 | $0.00250 | $0.00250 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
shader-cache-optimization-agent-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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Skill 255: shader-cache-optimization
Skill Identity
- Skill Name:
shader-cache-optimization - Tagline: Shader Cache Optimization to Eliminate Game Stuttering — Shader Compilation & Cache Performance Engineering analysis & decision-support harness.
- Current Phase: Phase 0 — Architecture & Research
- Folder:
D:\972026\255-shader-cache-optimization\
Problem This Skill Solves
This skill provides a structured, evidence-backed analytical workflow for Shader Compilation & Cache Performance Engineering. It gathers authoritative real-time and reference data, applies recognized domain methods, cross-references academic research, and delivers actionable outputs that are fully evidenced, risk/limitation-disclosed, and traceable to authoritative sources — continuously self-improving through an automated knowledge crawl pipeline.
Harness Flow Summary
/shader-cache-optimization invoked
│
├─ Step 1: sub-gather-requirements → Clarify the object of analysis, constraints, timeframe, available inputs, target audience, and language before any data fetching.
├─ Step 2: sub-evidence-collector → Fetch authoritative real-time and reference data for the object: current status/parameters, authoritative documents/standards, and recent developments from domain and academic sources.
├─ Step 3: sub-core-analysis → Optimize shader cache strategy to eliminate shader-compilation stutter in games via async/pre-build compilation and driver/DXVK cache tuning.
├─ Step 4: sub-knowledge-updater → Query SECOND-KNOWLEDGE-BRAIN.md for authoritative academic and professional evidence; surface citations with tier labels and flag gaps for the crawl pipeline.
├─ Step 5: sub-advisor → Synthesize all prior analysis into a risk-disclosed conclusion with a full evidence chain and recommended actions.
└─ Step 6: main (quality gate) → verify evidence hierarchy, disclosure, output polish
Sub-Skills
| skills/sub-gather-requirements.md | Clarify the object of analysis, constraints, timeframe, available inputs, target audience, and language before any data fetching. |
| skills/sub-evidence-collector.md | Fetch authoritative real-time and reference data for the object: current status/parameters, authoritative documents/standards, and recent developments from domain and academic sources. |
| skills/sub-core-analysis.md | Optimize shader cache strategy to eliminate shader-compilation stutter in games via async/pre-build compilation and driver/DXVK cache tuning. |
| skills/sub-knowledge-updater.md | Query SECOND-KNOWLEDGE-BRAIN.md for authoritative academic and professional evidence; surface citations with tier labels and flag gaps for the crawl pipeline. |
| skills/sub-advisor.md | Synthesize all prior analysis into a risk-disclosed conclusion with a full evidence chain and recommended actions. |
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.
- 3d ago First seen · 122 lines · 1,250 tokens per session scan A 67bd4a2561e4
shader-cache-optimization-agent-skill CLAUDE.md is an instructions file published in the GitHub repository dungnotnull/shader-cache-optimization-agent-skill (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,250 tokens to every session, about $0.0063 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
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.