Borrowing it
Nothing to install: this file belongs to haolange/InfinityRenderPipeline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/haolange/InfinityRenderPipeline/main/AGENTS.mdgit clone --depth 1 https://github.com/haolange/InfinityRenderPipelineWrote 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/haolange/infinityrenderpipeline/agents-md)<a href="https://agentmods.dev/instructions/haolange/infinityrenderpipeline/agents-md"><img src="https://agentmods.dev/badge/instructions/haolange/infinityrenderpipeline/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/haolange/infinityrenderpipeline/agents-md"><img src="https://agentmods.dev/badge/instructions/haolange/infinityrenderpipeline/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.09016 | $0.09016 |
| Opus 5.5 | $0.03606 | $0.03606 |
| Sonnet 5.5 | $0.01803 | $0.01803 |
| Haiku 4.5 | $0.00902 | $0.00902 |
Grade A, and why
InfinityRenderPipeline 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 today.
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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
InfinityRP contributor and agent specification
This document is normative for changes to com.infinity.render-pipeline. ARCHITECTURE.md describes the implementation. Docs/FeatureStatus.md records verification. Documentation~/index.md is the authoring manual. Docs/History/ is immutable evidence.
A silent fallback is not a fix. Console output with no errors has hidden ownership, order and lifetime defects, including a depth clear that left the Game view empty.
1. Work tracking
Track active work in the conversation task list. Do not create a root task ledger. Completed verification belongs in Docs/FeatureStatus.md.
Execution
Deliver the requested scope in the same interaction: decide, change, verify, and leave a connected result. Do not shrink it to a sample, a draft, or a proof of concept, and do not stop after the easy path, a plan, or a local patch that its callers never reach. Stages inside the interaction are allowed. Stop only when continuing could lose data, break an API, ABI, or serialized schema, force a wide or irreversible change, move a security or permission boundary, or change user-visible behavior that cannot be rolled back, or when the evidence supports no safe default. Ask in those cases. For every other ambiguity, state the default, why it was chosen, the risk, and the rollback, then finish the reversible work.
Do not create a git branch unless the user explicitly asks, or the session is already a worktree. Choosing an approach is not a branch. Docs/History does not authorize a push or new work.
Base a load-bearing decision on code, documents, logs, tests, historical assets, or an explicit user instruction. Keep the working state as a short summary that can be rechecked: goal size, evidence, decision, and what is still open.
Change only the requested code, documents, and the couplings that must move with them. Do not add flexibility, abstraction, or a repository-wide rewrite for later. Do not keep a second implementation, and do not add a compatibility shim to avoid deleting a replaced path. Principle 5 still requires that deletion once its consumers are closed.
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.
- today Changed · -71 lines · -2,612 tokens per session 48c05acc20ec
- yesterday Changed · +1 lines · +184 tokens per session 3b118dc40336
- 2d ago Changed · +32 lines · +1,617 tokens per session c86a24064e8b
- 3d ago Changed · +8 lines · +361 tokens per session c28896a3217c
- 4d ago Changed · +22 lines · +44 tokens per session 4d0b5d09c6da
- 1mo ago Changed · +10 lines · +594 tokens per session bc2acdb2dbc2
- 1mo ago Changed · +10 lines · +440 tokens per session e10fcc40fa2d
- 1mo ago Changed · +34 lines · +1,370 tokens per session 5921637800d1
- 1mo ago Changed · +32 lines · +1,211 tokens per session b6e425b652dd
- 1mo ago First seen · 190 lines · 5,807 tokens per session scan A 0a3bfdd6222b
InfinityRenderPipeline AGENTS.md is an instructions file published in the GitHub repository haolange/InfinityRenderPipeline (273 stars, last pushed yesterday), licensed MPL-2.0. It adds 9,016 tokens to every session, about $0.0361 per session on Opus 5.5. 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
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.