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/ackeskin/contexture/unitygit clone --depth 1 https://github.com/AcKeskin/contextureWhat 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 | $0.02332 | $0.02332 |
| Opus 5 | $0.01166 | $0.01166 |
| Sonnet 5 | $0.00466 | $0.00466 |
| Haiku 4.5 | $0.00233 | $0.00233 |
Grade A, and why
contexture unity.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 yesterday.
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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
unity rules
Auto-loaded by Copilot when editing files matching
**/*.cs. Generated fromarchitectural-rules/unity/— do not hand-edit.
Unity component-based design
- Component-based design only. Each MonoBehaviour owns one responsibility.
- No god components orchestrating unrelated systems. Split by concern and compose at the GameObject level.
- Prefer composition of small components over inheritance trees of MonoBehaviours.
Why: Unity's GameObject/component composition model fights inheritance. Working with the grain keeps prefabs reusable and testable.
Unity input via Input Actions on , not EnhancedTouch polling
For pointer/touch input in Unity (Input System 1.x+), the default approach is InputActionAsset with bindings on the abstract <Pointer> device:
Press— Button action bound to<Pointer>/pressPosition— Value/Vector2 action bound to<Pointer>/position
<Pointer> is the abstract base class for Mouse, Pen, and Touchscreen. One binding handles desktop editor (mouse), tablet (pen), and device (touch) without TouchSimulation.
Why:
- Unified surface. One binding covers mouse, pen, and touch. No editor-vs-device branches in input code.
- Survives synthetic-event testing. Input Actions consume Unity's input event stream, so
InputSystem.QueueStateEventworks in play-mode tests.EnhancedTouch.Touch.activeTouchespolling does not respond to queued state events. - Avoids the TouchSimulation gotcha.
TouchSimulation.Enable()creates the singleton but leaves its MonoBehaviour disabled in Input System 1.19 — no Touchscreen device registers, polling reads empty. Input Actions sidestep this entirely. - Documented modern path. Rebinding, control schemes, the PlayerInput component, and multi-device flows all build on Input Actions. EnhancedTouch polling is a dead end for any of those.
How to apply:
- Create an
InputActionAsset(*.inputactions) with at least a Gameplay map containingPress(Button →<Pointer>/press) andPosition(Value/Vector2 →<Pointer>/position). - Components that need input take
[SerializeField] InputActionAsset _actionsand look up the map + actions inAwake. - Subscribe in
OnEnable(action.performed += handler), unsubscribe inOnDisable. Callmap.Enable()/map.Disable()to gate. - Read companion values inside the callback via
otherAction.ReadValue<T>()rather than caching them inUpdate.
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.
- yesterday First seen · 149 lines · 2,332 tokens per session scan A 29245068fcc7
contexture unity.instructions.md is an instructions file published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,332 tokens to every session, about $0.0117 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
ccjk AGENTS.md
Instructions for miounet11/ccjk, covering repository guidelines, source of truth, behavior, validation and notes.
ccjk CLAUDE.md
Instructions for miounet11/ccjk: 持久知识唯一来源：docs/CLAUDE-NOTES.md（请优先阅读本文档）.
stenographer-mode copilot-instructions.md
Instructions for AkashAi7/stenographer-mode, covering steno mode — global instructions, contract, rules and levels.
capy CLAUDE.md
Claude Code instructions for serpro69/capy, covering claude.md, project, architecture, key packages and critical invariants.
.claude CLAUDE.md
Instructions for travisjneuman/.claude, covering claude.md — global development constitution, identity & role, p0 non-negotiables, optional shared agent operating layer and workflow.
gaster-code-releases AGENTS.md
AGENTS.md instructions for HereditaryDog/gaster-code-releases, covering repository guidelines, project structure & module organization, build, test, and development commands, desktop release workflow and docs workflow notes.