Borrowing it
Nothing to install: this file belongs to caretive-ai/project-careti. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/caretive-ai/project-careti/main/AGENTS.mdgit clone --depth 1 https://github.com/caretive-ai/project-caretiWrote 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/caretive-ai/project-careti/agents-md)<a href="https://agentmods.dev/instructions/caretive-ai/project-careti/agents-md"><img src="https://agentmods.dev/badge/instructions/caretive-ai/project-careti/agents-md/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/instructions/caretive-ai/project-careti/agents-md"><img src="https://agentmods.dev/badge/instructions/caretive-ai/project-careti/agents-md.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 | $0.01791 | $0.01791 |
| Opus 5 | $0.00896 | $0.00896 |
| Sonnet 5 | $0.00358 | $0.00358 |
| Haiku 4.5 | $0.00179 | $0.00179 |
Grade A, and why
project-careti 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 9d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Overview
- Careti: Cline 기반 포크이며, 핵심은 유지하고 careti-src/로 확장합니다.
- 이중 디렉토리:
.agents/(AI용, 토큰 최적화),.users/(사람용, 상세 설명)
IMPORTANT: 세션 시작 시 필수 작업
아래 파일들을 반드시 먼저 읽어주세요:
.agents/context/agents-rules.json- 프로젝트 핵심 규칙 (SoT).agents/context/ai-work-index.yaml- 작업 유형별 워크플로우 인덱스
필요 시 .agents/workflows/에서 관련 워크플로우를 온디맨드로 로드합니다.
Operations
- Proto 갱신:
npm run protos,npm run protos-go(proto 변경 시 순서대로 실행) - 컴파일:
npm run compile - CLI 컴파일:
npm run compile-cli(Go 바이너리 빌드) - 패키지:
npm run package
Desktop (Tauri)
주의: 루트에서 npm run dev:webview 실행 중이면 포트 충돌!
# 기존 vite 종료 (필수)
pkill -f "npm run dev:webview"
# 실행
cd desktop
npm run tauri dev # 개발 모드
npm run tauri build # 프로덕션 빌드
상세 문서: desktop/AGENTS.md, desktop/.agents/context/
Testing (자동 테스트)
테스트 명령어
| 명령어 | 설명 |
|---|---|
npm run test:unit |
백엔드 유닛 테스트 (mocha) |
npm run test:webview |
웹뷰 테스트 (vitest) |
npm run test:report |
전체 테스트 실행 및 요약 보고서 |
npm run test:report:json |
JSON 형식 테스트 결과 (AI 파싱용) |
AI 테스트 실행 가이드
- 코드 변경 후
npm run test:report:json실행 - JSON 출력에서
status필드 확인 (pass또는fail) - 실패 시
resultsDir경로에서 상세 로그 확인
주요 테스트 파일 위치
- Proto 변환 테스트:
src/shared/proto-conversions/models/__tests__/ - API Configuration 테스트:
src/shared/proto-conversions/models/__tests__/api-*.test.ts - StateManager 테스트:
src/shared/proto-conversions/models/__tests__/state-manager-api-config.test.ts - 웹뷰 테스트:
webview-ui/src/**/__tests__/
현재 테스트 상태 (2026-01-29)
- Unit: 769+ passing, 7 failing (VRM/Vision 관련)
- Webview: 140+ passing, 7 failing (i18n 조사 처리)
CLI Testing
테스트 실행
cd cli && go test ./e2e/... -v # 모든 E2E 테스트
cd cli && go test ./e2e/... -v -short # 빠른 테스트만 (통합 테스트 스킵)
cd cli && go test ./e2e/... -v -run TestInteractive # 특정 테스트만
테스트 구조 (cli/e2e/)
| 파일 | 설명 |
|---|---|
helpers_test.go |
테스트 유틸리티 (바이너리 경로, gRPC 헬퍼 등) |
cli_behavior_test.go |
CLI 동작 검증 (플래그, 명령어 구조) |
cli_output_test.go |
출력 형식 검증 |
interactive_mode_test.go |
Interactive/Yolo 모드 동작 |
start_list_test.go |
인스턴스 시작/목록 테스트 |
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.
- 9d ago First seen · 157 lines · 1,791 tokens per session scan A 6f40f860753e
project-careti AGENTS.md is an instructions file published in the GitHub repository caretive-ai/project-careti (47 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,791 tokens to every session, about $0.0090 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
vibe-coding-prompt-template backend.instructions.md
Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.