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/phodal/auto-dev/agents-mdgit clone --depth 1 https://github.com/phodal/auto-devWhat 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 | $0.00623 | $0.00623 |
| Opus 5 | $0.00311 | $0.00311 |
| Sonnet 5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
auto-dev AGENTS.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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Rules
- Kotlin Multiplatform: Always consider all platforms: JS, WASM, Desktop JVM, Android, iOS
- Build & Test: Always run build and tests before completing tasks
- Preserve Intent: If an existing solution doesn't work, preserve its intent
- Module Clean: Use
./gradlew :xxx:cleaninstead of global clean, avoid polluting global caches. - Test Scripts: Put temporary scripts under
docs/test-scripts - Logs: Check
~/.autodev/logs/autodev-app.logfor debugging - Code comments should be in English, for documentation and user-facing strings should be followed user's langauge
KMP Best Practices
- Use
expect/actualfor platform-specific code, for examplePlatform - Avoid emoji and UTF-8 in source code which WASM doesn't support
- @JsExport: Use concrete classes (not interfaces),
Promise(notFlow) - i18n: Run
./gradlew :mpp-ui:generateI18n4kFiles
Renderer System
When modifying CodingAgentRenderer, update ALL implementations:
- Kotlin:
DefaultCodingAgentRenderer,ComposeRenderer,JewelRenderer,ServerSideRenderer,JsRendererAdapter - TypeScript:
BaseRenderer.ts,CliRenderer.ts,ServerRenderer.ts,TuiRenderer.ts - VSCode:
mpp-vscode/src/bridge/mpp-core.ts,mpp-vscode/src/providers/chat-view.ts - JVM CLI:
CodingCliRenderer,ConsoleRenderer
Design System
- CLI/TUI: Use
semanticInk/semanticChalkfrommpp-ui/src/jsMain/typescript/design-system/ - Compose: Use
AutoDevColorsorMaterialTheme.colorScheme - NO hardcoded colors - always use design tokens
- Docs:
docs/design-system-color.md,docs/design-system-compose.md
Quick Commands
CLI Test:
./gradlew :mpp-core:jsNodeProductionLibraryDistribution
cd mpp-ui && npm run build && npm run start
IDEA Plugin:
cd mpp-idea && ../gradlew compileKotlin
cd mpp-idea && ../gradlew test --tests "cc.unitmesh.devins.idea.renderer.JewelRendererTest"
cd mpp-idea && ../gradlew buildPlugin
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 · 58 lines · 623 tokens per session scan A 51552b111ad7
auto-dev AGENTS.md is an instructions file published in the GitHub repository phodal/auto-dev (4,538 stars, last pushed 27d ago), licensed MPL-2.0. It adds 623 tokens to every session, about $0.0031 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
pydantic-ai AGENTS.md
Instructions for pydantic/pydantic-ai, covering your primary responsibility is to the project and its users, gathering context on the task, ensuring the task is ready for implementation, philosophy and requirements of all contributions.
ai-dev-gallery copilot-instructions.md
Instructions for microsoft/ai-dev-gallery, covering ai dev gallery - github copilot custom instructions, repository overview, pr review focus areas, security and performance.
vibeyard CLAUDE.md
Instructions for elirantutia/vibeyard, covering claude.md, what this is, build & run, testing and architecture.
instructor-php AGENTS.md
Instructions for cognesy/instructor-php, covering key reference files, monorepo root, individual subpackages, code style and agents package style.
DevoxxGenieIDEAPlugin GEMINI.md
Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…
iii AGENTS.md
AGENTS.md instructions for iii-hq/iii, covering agents.md, commands, setup, build and test.