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/touchlab/droidconkotlin/claude-mdgit clone --depth 1 https://github.com/touchlab/DroidconKotlinWrote 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/touchlab/droidconkotlin/claude-md)<a href="https://agentmods.dev/instructions/touchlab/droidconkotlin/claude-md"><img src="https://agentmods.dev/badge/instructions/touchlab/droidconkotlin/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 | $0.00397 | $0.00397 |
| Opus 5 | $0.00198 | $0.00198 |
| Sonnet 5 | $0.00079 | $0.00079 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
DroidconKotlin 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 4d 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
DroidconKotlin Development Guide
Build Commands
- Build:
./gradlew build - Clean build:
./gradlew clean build - Check (includes lint):
./gradlew check - Android lint:
./gradlew lint - Run tests:
./gradlew test - ktlint check:
./gradlew ktlintCheck - ktlint format:
./gradlew ktlintFormat - Build ios:
cd /Users/kevingalligan/devel/DroidconKotlin/ios/Droidcon && xcodebuild -scheme Droidcon -sdk iphonesimulator
Modules
- android: The Android app
- ios: The iOS app
- web: The Kotlin/JS web app
- shared: Shared logic code
- shared-ui: UI implemented with Compose Multiplatform and used by Android, iOS, and web
Libraries
- Hyperdrive: KMP-focused architecture library. It is open source but rarely used by other apps. See docs/HyperDrivev1.md
Code Style
- Kotlin Multiplatform project (Android/iOS/Web)
- Use ktlint for formatting (version 1.4.0)
- Follow dependency injection pattern with Koin
- Repository pattern for data access
- Compose UI for shared UI components
- Class/function names: PascalCase for classes, camelCase for functions
- Interface implementations: Prefix with
Default(e.g.,DefaultRepository) - Organize imports by package, no wildcard imports
- Type-safe code with explicit type declarations
- Coroutines for asynchronous operations
- Proper error handling with try/catch blocks
Claude Document Formats and Instructions
See APISummaryFormat.md and StructuredInstructionFormats.md
Architecture Notes
- App startup logic is handled in
co.touchlab.droidcon.viewmodel.ApplicationViewModel
Current Task
Cleaning up the app and prepping for release
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.
- 4d ago First seen · 46 lines · 397 tokens per session scan A fd3b42857f27
DroidconKotlin CLAUDE.md is an instructions file published in the GitHub repository touchlab/DroidconKotlin (1,146 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 397 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
kmp-api-lookup-mcp copilot-instructions.md
Copilot instructions for SuLG-ik/kmp-api-lookup-mcp, a project described as: Fast MCP server for Kotlin/Native Apple API lookup with local klib indexing, compact symbol cards, and on-demand metadata inspection.
skills AGENTS.md
AGENTS.md instructions for chrisbanes/skills, covering agents.md, when adding, renaming, or removing a skill, skill authoring checklist, evaluation result documentation and release/version system.
KtorMonitor AGENTS.md
Instructions for CosminMihuMDC/KtorMonitor, covering agents.md — ktormonitor, 1. project overview, 2. module structure, source-set layout (core) and 3. build, test, run.
tv-maniac GEMINI.md
Gemini CLI instructions for thomaskioko/tv-maniac, covering tv maniac agent rules, project overview, architecture & tech stack, core mandates & conventions and 1. modularization & dependencies.
ampere AGENTS.md
Instructions for socket-link/ampere, covering agents.md, concepts, development commands, build & test and code quality.
kormium AGENTS.md
Instructions for kormium/kormium, covering kormium for ai agents, mental model (read this first), define a schema, connect and inspect the sql without running it.