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/jason-hub-star/unityctl/claude-mdgit clone --depth 1 https://github.com/Jason-hub-star/unityctlWrote 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/jason-hub-star/unityctl/claude-md)<a href="https://agentmods.dev/instructions/jason-hub-star/unityctl/claude-md"><img src="https://agentmods.dev/badge/instructions/jason-hub-star/unityctl/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 | $0.05025 | $0.05025 |
| Opus 5 | $0.02513 | $0.02513 |
| Sonnet 5 | $0.01005 | $0.01005 |
| Haiku 4.5 | $0.00502 | $0.00502 |
Grade A, and why
unityctl 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 5d 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
unityctl 프로젝트 인덱스
unityctl 작업 시작 시 가장 먼저 읽는 진입 문서입니다. 이 문서만 읽어도 현재 단계, 규칙, 다음 행동을 빠르게 파악할 수 있게 유지합니다.
저장소 경계
- Write Repo:
.(저장소 루트 — clone 위치 무관)
시작 순서 (필수)
AGENTS.md(Codex) 또는CLAUDE.md(Claude) — 동일 정책 진입 문서docs/ref/architecture-mermaid.mddocs/status/PROJECT-STATUS.mddocs/ref/phase-roadmap.mddocs/ref/code-patterns.md(코드 작성 전 필수)
현재 상태 (2026-03-20)
- Phase 0~1B: Done
- Phase 1C (CI/CD): Done
- Phase 2A/2A+: Done (Foundation + Tools Metadata)
- Phase 2B (IPC Transport): Done
- Phase 2C (Async Commands): Done
- Phase 3B (Flight Recorder): Done
- Phase 3A (Session Layer): Done
- Phase 4A (Ghost Mode): Done
- Phase 3C (Watch Mode): Done
- Phase 4B (Scene Diff): Done
- Phase 5 (Agent Layer): Done
- Write API Phase A (PlayMode, PlayerSettings, AssetRefresh): Done
- Write API Phase B (GameObject CRUD, Scene Save): Done
- Write API Phase B.5 (Component CRUD): Done
- MCP Hybrid (unityctl_run + schema filter): Done
- Write API 확장 (Scene open/create, Undo/Redo, Phase C): Done
- Script Editing v1 (create/edit/delete/validate): Done
- Diagnostics (doctor + IPC 실패 자동 진단): Done
- P0 (Read API): Done (asset find/get-info/get-dependencies/reference-graph/get-labels/set-labels, gameobject find/get, component get, scene hierarchy, build-settings get-scenes/set-scenes)
- P3 (Screenshot/Visual Feedback): Done
- Tags & Layers + Editor Utility (tag/layer/console/define-symbols 10개 명령): Done
- Lighting & NavMesh (lighting bake/cancel/clear/get-settings/set-settings, navmesh bake/clear/get-settings 8개 명령): Done
- Physics Settings (physics get-settings/set-settings/get-collision-matrix/set-collision-matrix 4개 명령): Done
- Editor Utility 확장 (editor pause/focus-gameview/focus-sceneview 3개 명령): Done
- Script List (script list 1개 명령): Done
- MCP Context Optimization (C1 QueryTool + C2 Schema Category + C3 Description 경량화): Done (33→12 MCP 도구)
- Script Patch v2 (script patch — 줄 단위 삽입/삭제/교체): Done
- Script v2 (script-get-errors, script-find-refs, script-rename-symbol): Done
- UI Read Slice 1 (
ui find,ui get, UGUI-first): Done - UI Interaction Slice 1 (
ui toggle,ui input, deterministic state set): Done - Project Validate (
project validate— 게임 준비 상태 검증): Done - Mesh Create Primitive (
mesh create-primitive— 기본 3D 도형 생성): Done - Multi-Instance Routing Phase 1 (
editor current/select+ project-path selection fallback + target metadata): Done - Production Domain Expansion (camera list/get, texture get/set-import-settings, scriptableobject find/get/set-property, shader find/get-properties — 9개 명령): Done
- Visual Verification v2 Phase 1 (
workflow verify+ artifact-first verification bundle): Done - Visual Verification v2 Phase 1.5 (
playSmoke+ game-camera capture after settle): Done - Phase G: Asset Import/Export Extension (
asset-export,model-get-import-settings,audio-get-import-settings— 3개 명령): Done - Phase H: Animation Workflow Extension (
animation-list-clips/get-clip/get-controller/add-curve— 4개 명령): Done - Phase C: Profiler Commands (
profiler-get-stats/start/stop— 3개 명령): Done - Phase I-1: UGUI Enhancement (
ui-scroll/slider-set/dropdown-set— 3개 명령): Done - Phase D: Volume/PostProcessing (
volume-list/get/set-override/get-overrides,renderer-feature-list— 5개 명령, Reflection capability gating): Done - Phase E: Cinemachine (
cinemachine-list/get/set-property— 3개 명령, 2.x/3.x 런타임 감지): Done - Phase I-2: UI Toolkit (
uitk-find/get/set-value— 3개 명령, runtime UIDocument 체크): Done - MCP Prompts (
create_game_scene/debug_game/iterate_gameplay/setup_project— AI 워크플로우 가이드 4개): Done - CLI Feedback Fixes (CLI-012
prefab instantiate, CLI-014asset copy외부 경로, CLI-000 IPC 30초 메시지 타임아웃): Done - Token Optimization (status state 구분, hierarchy summary/maxDepth, component get summary, console get-entries dedupe): Done
- CLI Enhancement (profiler rendering stats, component add --name, component enable/disable, profiler --detailed): Done
- Exec Security Relaxation (BlockedPatterns-only, project code allowed): Done
- IPC Reload Resilience (heartbeat state 파일 + 클라이언트 reload-aware 재시도 + batch 폴백 억제): Done
- Type Introspection (
type describe— 라이브 타입 리플렉션 + Unity Manual 링크, summary-by-default): Done - IPC Reload Staleness Fix (
reloading상태를 15초가 아닌 리로드 예산 90초까지 신뢰 → 긴 도메인 리로드 중 IPC 드롭 방지) + asset-copy 목적지 프로젝트-루트 가드: Done - Spatial Grounding (
spatial describe/spatial check covers|inside|on-top-of|overlaps|aligned— 월드 AABB·true dimensions·표면 법선·술어 판정을 텍스트로. 스크린샷 없이 씬을 "측정된 공간 사실"로): Done (.NET 표면·핸들러 authored, Unity 컴파일은 에디터에서 확인) - 공식 CLI 벤치마크 + 흡수 사다리 (unattended lifecycle fix,
exec eval, 리졸버/속성명 통일,runtime status/logs): Done (전 항목 라이브 검증) - v0.6.1 Reliability Patch (
component get --fullhidden serialized state, macOS process inventory, MCP Registry metadata sync): Done (Unity 6000.3.16f1 라이브 검증) - v0.6.2 Distribution/Linux Patch (Claude Code/Codex workflow skill, NuGet README, Linux
/procprocess inventory): Done (Linux container/procprobe 검증) - v0.6.3 IPC/Validation Hardening (listener shutdown race + bounded ping readiness probe + validation failure semantics): Done (Unity labs + 3-OS CI, Windows #12/#13 reporter 재검증 대기)
- Local Code Intelligence Slice (
script find-refsCore local scanner, Editor/IPC 불필요): Done (closed-project 4.34s→0.21s, 20.7x) - Distribution Ladder P1~P5 (README hero GIF, 저장소 메타, self-contained single-file 릴리스,
mcp install+ Unity 상태창, README 603→199줄): Done (Unity 6000.3.16f1 batchmode 컴파일 검증, 4 RID publish 재현)
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.
- 5d ago First seen · 226 lines · 5,025 tokens per session scan A 0e2be094a859
unityctl CLAUDE.md is an instructions file published in the GitHub repository Jason-hub-star/unityctl (18 stars, last pushed 15d ago), licensed MIT. It adds 5,025 tokens to every session, about $0.0251 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
maui uitests.instructions.md
Instructions for dotnet/maui, covering ui testing guidelines for .net maui, ui test structure, two-project requirement, base class and infrastructure and naming conventions.
maui ci-copilot-pipeline-security.instructions.md
Security rules for the Copilot PR-review pipeline. Read before editing.
maui performance-hotpaths.instructions.md
Instructions for dotnet/maui, covering performance-critical path rules, hot paths in maui, allocation avoidance, caching and invalidation and collection iteration.
maui collectionview-windows.instructions.md
Instructions for dotnet/maui, covering collectionview — windows (items/ handler), winui listview/itemsrepeater patterns, data source and change notifications, layout configuration and cross-platform consistency.
codex-provider-sync AGENTS.md
Instructions for Dailin521/codex-provider-sync, covering ai / agent operator guide, vnext architecture baseline, goal, choose the interface and safe operating flow.
Grace AGENTS.md
AGENTS.md instructions for ScottArbeit/Grace, covering agent instructions, agent quickstart (local), issue tracking, development process and markdown guidelines.