Borrowing it
Nothing to install: this file belongs to seungyeop-lee/beads-starter. 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/seungyeop-lee/beads-starter/main/AGENTS.mdgit clone --depth 1 https://github.com/seungyeop-lee/beads-starterWrote 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/seungyeop-lee/beads-starter/agents-md)<a href="https://agentmods.dev/instructions/seungyeop-lee/beads-starter/agents-md"><img src="https://agentmods.dev/badge/instructions/seungyeop-lee/beads-starter/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/seungyeop-lee/beads-starter/agents-md"><img src="https://agentmods.dev/badge/instructions/seungyeop-lee/beads-starter/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 | $0.05968 | $0.05968 |
| Opus 5 | $0.02984 | $0.02984 |
| Sonnet 5 | $0.01194 | $0.01194 |
| Haiku 4.5 | $0.00597 | $0.00597 |
Grade C, and why
beads-starter AGENTS.md scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
3. **`curl | bash` 경로가 동작해야 함** — 스크립트는 stdin으로 파이프되어 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. **`curl | bash` 경로가 동작해야 함** — 스크립트는 stdin으로 파이프되어 How it starts
The opening of the file, as written. The whole thing — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents
프로젝트 개요
beads-starter는 beads 워크플로우
규약을 프로젝트에 적용하는 두 가지 모드를 제공합니다:
- 항시 발동 모드(bash 설치형) — 대상 레포의
AGENTS.md등에 콘텐츠를 주입해 매 세션 자동 적용. 진입점은always-on/beads-starter.sh이며 루트beads-starter.sh는 URL 안정성을 위한 thin shim입니다. - 명시적 발동 모드(Claude Code 또는 Codex 플러그인) —
on-demand/하위 콘텐츠를 사용자가 명시적으로 호출했을 때만 발동. 단일 소스on-demand/skills/를 두 도구가 공유합니다:- Claude Code:
on-demand/.claude-plugin/plugin.json을 통해 marketplace로 배포, 슬래시 커맨드(/bds-workflow,/bds-setup,/bds-status). - Codex:
.agents/plugins/marketplace.json에서on-demand/를 플러그인 source로 가리키고,on-demand/.codex-plugin/plugin.json이 같은on-demand/skills/를 참조합니다. 호출은/skillsUI나$<name>멘션.on-demand/codex-installer.sh는 예전 direct-skill 설치본 제거용 legacy cleanup 스크립트입니다.
- Claude Code:
이 레포 자체는 beads 워크플로우를 사용하지 않습니다. .beads/ 초기화,
beads 이슈 등록, bd 상태 전환은 적용 대상 레포에 들어가는 운영 규칙이지
이 starter 프로젝트의 작업 절차가 아닙니다.
구조
beads-starter/
├── .agents/plugins/marketplace.json # Codex self-marketplace 진입점
├── beads-starter.sh # 루트 shim — URL 안정성용 thin wrapper
├── always-on/ # 항시 발동 모드
│ ├── beads-starter.sh # 정본 bash 진입점
│ └── payload/ # 대상 레포에 주입되는 콘텐츠
│ ├── gitignore.part
│ ├── AGENTS.md.part
│ └── docs/beads-starter/
│ ├── bd-setup.md.part
│ ├── beads-commands.md.part
│ ├── issue-content.md.part
│ ├── issue-content-bug.md.part
│ ├── issue-content-task.md.part
│ ├── issue-content-feature.md.part
│ ├── issue-content-chore.md.part
│ └── issue-content-epic.md.part
├── on-demand/ # 명시적 발동 모드
│ ├── .claude-plugin/plugin.json # Claude Code 플러그인 메타
│ ├── .codex-plugin/plugin.json # Codex 플러그인 메타
│ ├── codex-installer.sh # Codex legacy direct-skill cleanup
│ └── skills/ # 두 도구가 공유하는 단일 소스
│ ├── bds-workflow/ # 10단계 워크플로우 + 보조 파일
│ │ ├── SKILL.md
│ │ ├── issue-content.md
│ │ ├── issue-content-bug.md
│ │ ├── issue-content-task.md
│ │ ├── issue-content-feature.md
│ │ ├── issue-content-chore.md
│ │ ├── issue-content-epic.md
│ │ ├── shell-safety.md
│ │ ├── commit-rules.md
│ │ └── commands.md
│ ├── bds-setup/SKILL.md
│ └── bds-status/SKILL.md
└── .claude-plugin/marketplace.json # self-marketplace 진입점
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 · 418 lines · 5,968 tokens per session scan C c907c08e5b6e
beads-starter AGENTS.md is an instructions file published in the GitHub repository seungyeop-lee/beads-starter (1 stars, last pushed 3mo ago), licensed MIT. It adds 5,968 tokens to every session, about $0.0298 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.