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 rules/baek-labs/hames/cursorrulesgit clone --depth 1 https://github.com/baek-labs/hamesWhat 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 | $0.00525 | $0.00525 |
| Opus 5 | $0.00262 | $0.00262 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
cursorrules 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.
What it actually says
HAMES SYSTEM CURSOR ENTRY v5.5 [STRATEGIC_OS — Redirect to CLAUDE.md]
Updated: 2026-06-16 Cursor의 자동 로드 진입 파일. **단일 진실 출처는
CLAUDE.md**이다.
Entry Redirect
이 워크스페이스의 모든 운영 규칙은 CLAUDE.md에 정의되어 있다.
시동 시 아래 6개 파일을 순서대로 읽어 컨텍스트를 구성한다:
CLAUDE.md(커널).cursor/rules/prompt_engineering.md.cursor/rules/context_engineering.md.cursor/rules/agent_engineering.md.cursor/rules/harness_engineering.mdarsenal/CLAUDE.md
Cursor는
@import자동 펼침이 없을 수 있다.CLAUDE.md의@경로라인을 보면 그 파일들도 명시적으로 추가 로드한다.
⚠ MANDATORY ENFORCEMENT
방어선 1/2의 단일 정의 위치는 .cursor/rules/enforcement.md다.
시동 시 위 6개 파일에 더해 enforcement.md도 명시적으로 읽고 그 안의 규칙을 따른다.
Cursor 전용 보충
.cursorrules로드 시점에 규칙 활성화 완료. 별도 스크립트 실행 불필요.HamesSystem 적용= 규칙 활성화 확인 트리거. 스크립트/파일 생성 없음.- 자연어 트리거 해석은
context_engineering.md[2] CURRENT MODE 섹션의 단일 정의를 따른다 (HamesSystem 적용,<Workspace> 모드로,<Workspace> 모드로 고정,고정 해제).
핸드오프 처리
ai_comm/Memory/.hames_start_gemini.md가 존재하면 핸드오프 부트스트랩으로 읽는다.Session lock: ON명시 시에만 active workspace/agent/task를 고정한다.Session lock: OFF또는 누락 시 부트스트랩은 권고이며 사용자 지시가 우선.- 부트스트랩 파일은 정본(Standard). 세션 상태 변경을 기록하지 않으며 그대로 유지한다.
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 · 45 lines · 525 tokens per session scan A 3d88e821d9a8
cursorrules is a cursor rule published in the GitHub repository baek-labs/hames (5 stars, last pushed 1mo ago), licensed MIT. It adds 525 tokens to every session, about $0.0026 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 cursor rules, from other repositories
sofagent
Cursor rule "sofagent" from KongFangXun/sofagent, covering sofagent · cursor 适配（薄挂载）, 会话开始时按序加载（四层加载链）, 审计强制（平台无关） and 连接 mcp server.
050-plan
When the user types /plan or asks to create a project plan, feature PRD, or retrospective.
checkpoint
Write a committed handoff checkpoint so a fresh session can resume with zero loss. Use when crossing the 40% context line, on every stage transition, and at session end. Writes .trace/checkpoints/ - .md while the agent is still sharp.
lean
Answer densely. Cut filler, keep all technical signal.
orchestrator-main
Rules for the main orchestrator agent in multi-agent workflows.
Documentation
Professional Documentation Standards for GitHub OSS Projects - Developer, Collaborator, and User Readiness.