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/sinanata/unity-3d-to-sprite-baker/copilot-instructionsgit clone --depth 1 https://github.com/sinanata/unity-3d-to-sprite-bakerWrote 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/sinanata/unity-3d-to-sprite-baker/copilot-instructions)<a href="https://agentmods.dev/instructions/sinanata/unity-3d-to-sprite-baker/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/sinanata/unity-3d-to-sprite-baker/copilot-instructions.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 5.1 | $0.00399 | $0.00399 |
| Opus 5 | $0.00199 | $0.00199 |
| Sonnet 5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
unity-3d-to-sprite-baker copilot-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 6d 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
GitHub Copilot instructions
This repository follows the cross-tool AGENTS.md standard. Read /AGENTS.md for the full guide: the SpriteBaker API, the enqueue → cache → bind flow, the material rules, build and preview commands, and the pull-request checklist.
The rules that matter most:
- Baking is runtime + async (coroutine), one frame per Unity frame — not editor-only, not synchronous. Enqueue with
SpriteAtlasBaker.Instance.Enqueue, then read withSpriteAtlasCache.TryGet/IsReady, orAnimatedSpriteRenderer.Bind(key)early (it waits for the bake). - The playback material is URP/Unlit from
Resources/SpriteBakerAtlasUnlitTemplate.mat, NOT theAtlasCutout.shader. Don't swap innew Material(Shader.Find("SpriteBaker/AtlasCutout"))— a custom URP shader compiled at runtime renders black on WebGL2. Copy the wholeAssets/SpriteBaker/folder (includingEditor/and the.mat). - Render with URP's
SingleCameraRequest, notCamera.Render()(a no-op on WebGL2 URP), and always stage the capture light rig — a URP/Lit character at the (2000, 2000, 0) capture origin renders black without it. CaptureRotationcomposes onto the authored rotation (Kenney AC2 =Euler(0,180,0)); setSampleAnimationTargetPathfor child-relative rigs.- Keep the per-frame
yield return nullin the bake loop — without it every captured frame shows the same pose. - No
using LeapOfLegends.*. Runtime code lives in theSpriteBakernamespace; demo code underSpriteBaker.Demo.
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.
- 6d ago First seen · 13 lines · 399 tokens per session scan A cc696b17412b
unity-3d-to-sprite-baker copilot-instructions.md is an instructions file published in the GitHub repository sinanata/unity-3d-to-sprite-baker (43 stars, last pushed 1mo ago), licensed MIT. It adds 399 tokens to every session, about $0.0020 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
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.
base-building-trap-defense-design-agent-skill CLAUDE.md
Instructions for dungnotnull/base-building-trap-defense-design-agent-skill, covering claude.md — skill 250: base-building-trap-defense-design, skill identity, problem this skill solves, harness flow summary and sub-skills.
trident-mcp AGENTS.md
Instructions for mordor-forge/trident-mcp, covering agents.md, what this is, build and test, single-file verification and e2e tests.
unreal-mcp-additional-tools CLAUDE.md
Claude Code instructions for nodormu/unreal-mcp-additional-tools, covering claude.md, what this is, commands, architecture and transports (src/transports/).