Borrowing it
Nothing to install: this file belongs to CIrcui-try/Circuit. 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/CIrcui-try/Circuit/main/AGENTS.mdgit clone --depth 1 https://github.com/CIrcui-try/CircuitWrote 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/circui-try/circuit/agents-md)<a href="https://agentmods.dev/instructions/circui-try/circuit/agents-md"><img src="https://agentmods.dev/badge/instructions/circui-try/circuit/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/circui-try/circuit/agents-md"><img src="https://agentmods.dev/badge/instructions/circui-try/circuit/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 | $0.00772 | $0.00772 |
| Opus 5.5 | $0.00309 | $0.00309 |
| Sonnet 5.5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
Circuit 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 2mo 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
슬래시 커맨드 공통 규칙
.claude/commands/, .claude/skills/, .codex/commands/, .codex/skills/, .agents/skills/ 안의 모든 워크플로에 공통으로 적용한다. 개별 커맨드와 스킬은 이 규칙을 다시 명시하지 않는다.
Claude / Codex 양립
.claude/commands/는 Claude 전용 슬래시 커맨드다..claude/state,mcp__linear-server__*,TodoWrite,AskUserQuestion,ExitPlanMode같은 Claude 전용 표현을 Codex 방식으로 바꾸지 않는다..claude/skills/는 Circuit 앱의 Claude 스킬 디스커버리용 미러다. Claude 커맨드와 같은 런타임 표현을 유지한다..codex/commands/는 Codex 슬래시 커맨드 전용이다..codex/state와 Codex에서 사용할 수 있는 도구명을 기준으로 유지한다..codex/skills/는 Circuit 앱의 Codex 스킬 디스커버리용 미러다..agents/skills/와 같은 Codex 런타임 표현을 유지한다..agents/skills/는 Codex 프로젝트 스킬용 원본이다. Claude 커맨드를 덮어쓰거나 대체하지 않고, Codex 앱에서 재사용할 워크플로 지침으로 관리한다.- 같은 워크플로 이름을 공유하더라도 Claude와 Codex의 상태 디렉터리, MCP 서버명, 도구명은 런타임별로 분리한다.
Plan mode 호환
Plan mode 가 활성화된 상태에서 워크플로가 호출되어도 거부하지 말 것. Plan mode 의 정의는 "계획만 세우고 승인 후 실행" 이므로 다음 순서로 처리한다:
- 읽기 전용 도구로 커맨드가 실제로 수행할 작업 (워크트리 경로, 변경 파일, 커밋 단위 후보, 실행할 명령) 을 충분히 파악한다.
- plan 파일에 그 내용을 구체적으로 정리한다. "plan mode 라서 못 한다" 같은 답변은 금지.
- Claude 에서는
ExitPlanMode, Codex 에서는 Codex Plan mode 승인 흐름으로 승인 요청한다. 사용자가 plan mode 를 빠져나오면 정리한 계획대로 실제 절차를 그대로 이어 수행한다.
커밋 / GitHub 계정
- 개인별 커밋 author / committer / GitHub CLI active account 정책은 공개 추적 파일에 기록하지 않는다. 필요한 경우
AGENTS.local.md같은 ignored 로컬 파일이나 사용자 홈 디렉터리 설정에 둔다. - PR 제목, PR 본문, 커밋 메시지는 반드시 영어로 작성한다. 한국어를 쓰지 않는다.
- 커밋 메시지에
Co-Authored-By트레일러를 추가하지 않는다. - GitHub CLI(
gh) 를 실제로 호출하는 워크플로에서는 첫gh명령 직전에만gh-auth-check스킬 절차로 로그인 상태를 확인한다. 로그인되어 있지 않으면 작업을 중단하고 사용자에게 알린다. - 앱 시작, 저장소 읽기, 로컬 구현, 테스트, 커밋-only 작업처럼
gh를 호출하지 않는 흐름에서는gh-auth-check를 선제 실행하지 않는다.
모든 답변은 한국어로 합니다
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.
- 2mo ago First seen · 31 lines · 772 tokens per session scan A 992bb41198ab
Circuit AGENTS.md is an instructions file published in the GitHub repository CIrcui-try/Circuit (5 stars, last pushed 5mo ago), licensed MIT. It adds 772 tokens to every session, about $0.0031 per session on Opus 5.5. 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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.