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/mercurypark/oc-setup/agents-mdgit clone --depth 1 https://github.com/mercuryPark/oc-setupWrote 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/mercurypark/oc-setup/agents-md)<a href="https://agentmods.dev/instructions/mercurypark/oc-setup/agents-md"><img src="https://agentmods.dev/badge/instructions/mercurypark/oc-setup/agents-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 | $0.00999 | $0.00999 |
| Opus 5 | $0.00500 | $0.00500 |
| Sonnet 5 | $0.00200 | $0.00200 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
oc-setup 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
oc-setup
OpenCode 초기 환경 세팅 플러그인 + CLI (TypeScript/Bun). 설계 문서는 DESIGN.md에 있다.
Communication Rules
- User's Question Language: Always respond in the same language as the user's question
- Language Detection: Automatically detect the language of each user query
- Consistency: Never switch languages mid-conversation or mid-response
- Technical Terms: Technical terms may remain in English if no appropriate translation exists
- Code Comments: Follow project conventions (English for code, user's language for explanations)
핵심 원칙
- DESIGN.md가 진실의 원천이다. 구현 시 항상 DESIGN.md를 먼저 읽고 따를 것.
- 구현 순서는 DESIGN.md 섹션 12 Phase 2를 따른다. Step 1 → 9 순서.
- 한 번에 하나의 Step만 구현한다.
Project Structure
oc-setup/
├── src/
│ ├── index.ts # 플러그인 진입점 (@opencode-ai/plugin)
│ ├── cli.ts # CLI 진입점 (commander)
│ ├── tools/ # 플러그인 tool 정의 (setup_init, setup_migrate 등)
│ ├── core/ # 비즈니스 로직 (config, agents-md, command, skill 생성)
│ ├── migrate/ # 마이그레이션 (claude-code, cursor, aider)
│ ├── preset/ # 프리셋 레지스트리 및 적용
│ ├── provider/ # Provider/모델 레지스트리 및 추천
│ ├── prompt/ # 대화형 위자드 (@inquirer/prompts)
│ ├── doctor/ # 환경 진단
│ ├── validator/ # 설정 검증
│ └── types/ # 타입 정의
├── templates/ # 내장 템플릿 (.md, .json)
└── test/ # bun:test 테스트
Code Standards
- TypeScript strict mode
- Bun 런타임
- 에러 처리: try/catch + 의미 있는 에러 메시지, 절대 silent fail 하지 않음
- 모든 exported 함수/타입에 JSDoc 주석
- 외부 의존성 최소화. 표준 라이브러리로 해결 가능하면 표준 사용
Dependencies
핵심:
@opencode-ai/plugin— 플러그인 SDKzod— 스키마 검증 (플러그인 SDK 의존)commander— CLI 프레임워크
CLI 모드:
@inquirer/prompts— 대화형 프롬프트
선택:
yaml— Aider .aider.conf.yml 파싱용 (필요시만)
불필요한 의존성 추가 금지.
Testing
bun test으로 전체 테스트 실행- test/ 디렉토리에 src/ 구조 미러링
- test/fixtures/ 에 Claude Code, Cursor, Aider 샘플 설정 배치
Plugin Architecture
- src/index.ts는
Plugin타입을 export하는 async 함수 - tool은
tool()헬퍼로 정의. args는 zod 스키마. - tool의 execute 함수는 반드시 string을 반환
- 플러그인 context:
{ client, project, $, directory, worktree }
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.
- 3d ago First seen · 97 lines · 999 tokens per session scan A 30fc2c5c2b8d
oc-setup AGENTS.md is an instructions file published in the GitHub repository mercuryPark/oc-setup (2 stars, last pushed 4mo ago), licensed MIT. It adds 999 tokens to every session, about $0.0050 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.