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 rules/haolange/infinityrenderpipeline/unity-refresh-iterategit clone --depth 1 https://github.com/haolange/InfinityRenderPipelineWhat 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 | $0.00380 | $0.00380 |
| Opus 5 | $0.00190 | $0.00190 |
| Sonnet 5 | $0.00076 | $0.00076 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
unity-refresh-iterate 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 2d 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
Unity Refresh + Log + Frame Iterate
After any InfinityRP code/shader change, do not wait for the user to compile.
- Confirm the open editor via
D:\Projects\Unity\InfinityExample\Library\EditorInstance.json. Do not launch a second Unity or-batchmodewhile that editor is open. - Foreground that Unity window and trigger
Assets > Refresh(Ctrl+R) usingTools/RefreshUnityEditor.ps1. - Wait until
D:\Projects\Unity\InfinityExample\Logs\Editor.loggrows past the pre-refresh mark and then stays stable. - Diagnose only new log after the mark. Fix the first real owner/order/lifetime/shader-contract defect.
- Capture the frame with
Tools/CaptureUnityWindow.ps1and inspect the image. Console-clean is not render-correct: a depth-clear regression once held the Console at 0 errors while the Game view rendered nothing. Always capture after touching clears, depth, attachments, pass order, or present. - Forbidden as a "fix":
if (shader == null) returnin execute, dummy textures, disabling a designed path to silence Console, fake history, orcount = 0dispatches. - Unimplemented features must not be recorded. Required producers (Lighting, TAA when that path is active, Display) must fail at record/setup if their contract is broken.
- Repeat refresh → log → frame → first-principles fix until the new log window has no InfinityRP flood and the captured frame is correct. Keep
TODO(UNVERIFIED)on any result that was checked by log only.
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.
- 2d ago First seen · 18 lines · 380 tokens per session scan A 029f49363faf
unity-refresh-iterate is a cursor rule published in the GitHub repository haolange/InfinityRenderPipeline (271 stars, last pushed 16d ago), licensed MPL-2.0. It adds 380 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 cursor rules, from other repositories
architecture
Architectural and cross-package changes — dependency direction, editor/runtime boundaries, scene schema, persistence, renderer packages. Use when changing package boundaries, serialized formats, or multiple layers. Do not apply to localized UI, styling, or test-only edits.
unity-performance
Cursor rule "unity-performance" from Common-ka/ai-agent-unity-rules, covering unity performance rules, update/fixedupdate/lateupdate, usage rules, object pooling (unityengine.pool) and addressables (not resources).
monobehaviour-lifecycle
Correct usage of MonoBehaviour lifecycle methods.
sweep-benchmarks
Audit xrspatial modules for asv benchmark coverage gaps: missing benchmarks, backend parameterization gaps, unrepresentative inputs, broken or silently-skipped benchmarks.
cpp
Cursor rule "cpp" from maddevsio/shared_cursor_rules, covering c++ programming guidelines, basic principles, nomenclature, functions and data.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.