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.
git clone --depth 1 https://github.com/Meet-Miyani/compose-skillWrote 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/rules/meet-miyani/compose-skill/reference-file-standards)<a href="https://agentmods.dev/rules/meet-miyani/compose-skill/reference-file-standards"><img src="https://agentmods.dev/badge/rules/meet-miyani/compose-skill/reference-file-standards/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/rules/meet-miyani/compose-skill/reference-file-standards"><img src="https://agentmods.dev/badge/rules/meet-miyani/compose-skill/reference-file-standards.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 | $0.00000 | $0.01158 |
| Opus 5.5 | $0.00000 | $0.00463 |
| Sonnet 5.5 | $0.00000 | $0.00232 |
| Haiku 4.5 | $0.00000 | $0.00116 |
Grade A, and why
reference-file-standards 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reference File Writing Standards
Every reference file must be token-efficient. Agents already know standard APIs — provide the kit's rules, pitfalls, and project-specific decisions, not tutorials.
File Structure
- Line 1:
# Title— concise topic name - Next line:
Load when: …(orLoad this when …) — the task that needs this file, in one line - Optional
## Choose— a short yes/no decision tree when the file covers a real choice - Rule sections — numbered rules: bold rule, one-line reason,
*Prevents:*the failure it stops; tag(non-negotiable)or(default)where it matters ## Red flags(when real rationalizations exist) —| Thought | Reality |table, first-person thought → rebuttal citing the rule number## Verification— checkbox gates, each a command or a yes/no condition- No long Table of Contents — agents navigate by headings; a file well past 100 lines may open with a 5–10 line contents list
Writing Rules
| Rule | Do | Don't |
|---|---|---|
| Tables over prose | | Issue | Fix | table |
Multi-paragraph explanations |
| Rules over explanations | State the rule directly | Explain "why" unless non-obvious |
| Examples over descriptions | One WRONG/RIGHT code pair | Three paragraphs describing the concept |
| No tutorial content | Show the pattern/pitfall | Explain what StateFlow or PagingSource is |
| Third-party APIs as gotchas | One line naming the API + "verify against current docs" | Setup walkthroughs, pinned versions |
| Trim filler words | Direct statements | "It is important to note that...", "In order to...", "You should consider..." |
DRY Cross-Referencing
Each rule has ONE canonical home. Other files point to it instead of duplicating; a pointer into another skill names that skill.
| Concept | Canonical home | Other files do |
|---|---|---|
MVI contract, BaseViewModel, effects, collection at the Route |
compose-architecture/references/mvi-contract.md |
One-line rule + pointer |
State ownership, drafts, SavedStateHandle |
compose-architecture/references/state-ownership.md |
Pointer |
Failure types, launchGuarded, UI error tiers |
compose-architecture/references/error-handling.md |
Pointer |
| Flows, scopes, dispatchers | compose-architecture/references/coroutines-flow.md |
Pointer |
| Koin modules, lifetimes, ViewModel params | compose-architecture/references/dependency-injection.md |
1–2 line binding example + pointer |
| Navigation 3 keys, back stack, results | compose-architecture/references/navigation.md |
Pointer |
| Existing Hilt / MVVM / Navigation 2 projects | compose-architecture/references/existing-projects.md |
Pointer |
| ViewModel test setup, fakes, test dispatchers | compose-feature/references/testing.md |
Domain-specific fake + pointer |
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 Changed · -23 lines 3e6d498fb885
- 1mo ago First seen · 119 lines · 0 tokens per session scan A ad56720dfd71
reference-file-standards is a cursor rule published in the GitHub repository Meet-Miyani/compose-skill (304 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,158 tokens. 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 cursor rules, from other repositories
compose-performance
Compose performance: stability annotations (@Stable, @Immutable), strong-skipping in Kotlin 2.x, key-based recomposition, derivedStateOf, remember{} keys, deferred reads, Compose previews + Paparazzi for screenshot tests.
android-project
Core behavior rules for AI agents working on this Android project.
android-project-bootstrap
Walks a developer through bootstrapping a BRAND-NEW Android project for agentic CLI delivery — creating the Firebase project, registering the Android app, setting up App Distribution, creating the Google Play Console listing, wiring API access, and installing the Gradle plugins. Use when the user says they're starting…
technical_design_documentation_rule
Rule: Guideline for creating a Technical Design Document for a new feature.
android-project-onboarding
Walks a new developer through one-time setup of an EXISTING configured Android project from a blank macOS install — JDK, Android SDK, AVD, scrcpy, shell env vars, credential files, and a smoke-test build. Assumes Firebase project + Play Console listing already exist; user just needs to acquire credentials. Use when…
implementation_rule
Rule: Define the implementation guidelines for a task checklist – following Clean Architecture standards for Android-Kotlin.