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/androidgit 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 | $0.00882 | $0.00882 |
| Opus 5 | $0.00441 | $0.00441 |
| Sonnet 5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
contexture android.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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
android rules
Auto-loaded by Copilot when editing files matching
**. Generated fromarchitectural-rules/android/— do not hand-edit.
Android Lifecycle Discipline
Never hold a static or long-lived reference to an Activity, Fragment, View, or their Context. Use applicationContext for needs that outlive a single screen. A static Activity ref keeps the whole view hierarchy alive past onDestroy, leaking memory. (Android docs — Activity lifecycle)
Do not store UI state in the Activity/Fragment. Hold it in a ViewModel (survives rotation/config changes) plus SavedStateHandle / saved instance state for process death. The system destroys and recreates the Activity on configuration change; instance fields are lost. (Android docs — Handle configuration changes)
Register and unregister listeners, receivers, sensors, and observers symmetrically: acquire in onStart/onResume, release in the paired onStop/onPause. Asymmetric registration leaks callbacks and double-fires after recreation. (Android docs — Activity lifecycle)
Why: The framework owns Activity/Fragment lifetime and recreates them on configuration changes, so any UI state or Context captured in instance/static fields either leaks or is silently lost. Hoisting state into a lifecycle-aware ViewModel and binding resource acquisition to symmetric lifecycle callbacks keeps ownership explicit and prevents both leaks and stale callbacks. Source: Android developer documentation.
Android Resources and Manifest Discipline
Never hardcode UI strings, dimensions, colors, or sizes in code or layouts. Put them in res/values/ (strings.xml, dimens.xml, colors.xml) and provide configuration-qualified variants (values-fr/, values-night/, values-sw600dp/). Externalized resources enable localization, theming, and device adaptation. (Android docs — App resources)
Declare every permission in the manifest, and for dangerous permissions request them at runtime and handle denial gracefully. Assuming a permission is granted without checking crashes on modern Android. Request only what the feature needs. (Android docs — Permissions on Android)
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 · 40 lines · 882 tokens per session scan A bce9b23db7aa
contexture android.instructions.md is an instructions file published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 882 tokens to every session, about $0.0044 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
paseo CLAUDE.md
Claude Code instructions for getpaseo/paseo, covering claude.md, repository map, docs, writing docs and doc voice.
cc-pocket AGENTS.md
Instructions for heypandax/cc-pocket, covering agents.md — cc-pocket, ⚠️ 本机 daemon 操作铁律(最重要,先读这一段), 改完 daemon 代码要更新本机 daemon —— 只用这一条命令, 绝对不要做(每一条都会制造第二个 daemon → 立刻不可用) and 必须知道的两个反直觉事实(本机环境).
Aether AGENTS.md
AGENTS.md instructions for Zhou-Shilin/Aether, a project described as: A stunning, localized, general-purpose AI Agent for Android, iOS & Mac. | Aether 扶摇.
automate CLAUDE.md
Instructions for kobiton/automate, covering claude.md, getting started, commands, single test file and architecture.
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).