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 commands/bunhine0452/ocul-pm/helpgit clone --depth 1 https://github.com/bunhine0452/Ocul-PMWrote 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/commands/bunhine0452/ocul-pm/help)<a href="https://agentmods.dev/commands/bunhine0452/ocul-pm/help"><img src="https://agentmods.dev/badge/commands/bunhine0452/ocul-pm/help.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 5.1 | $0.00035 | $0.00534 |
| Opus 5 | $0.00017 | $0.00267 |
| Sonnet 5 | $0.00007 | $0.00107 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
help 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 today.
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
/oculpm:help
아래 레퍼런스 카드를 사용자에게 그대로 보여주고, 상황에 맞는 다음 한 걸음을 한 줄로 추천하세요 (.oculpm/ 이 없으면 /oculpm:project_init, 활성 플랜이 있으면 /oculpm:next).
커맨드 5종
| 커맨드 | 언제 |
|---|---|
/oculpm:project_init |
새 저장소를 ocul-pm 추적 대상으로 초기화 (한 번) |
/oculpm:inception |
새 프로젝트/기능 영역 설계 — 리서치→인터뷰→3-depth 계획 |
/oculpm:next |
구현 루프 — 다음 미완 리프 구현→검증→일지→플랜 갱신 |
/oculpm:standup |
오늘/최근 작업 요약 보고 |
/oculpm:help |
이 카드 |
MCP 도구 5종 (앱 설치 시)
journal_write(일지 작성) · plan_status(플랜 조회 — 응답의 plans[].hash 가 plan_update 의 base_hash 재료) · plan_update(항목 상태 갱신 — base_hash 필수, 병렬 세션 보호) · plan_create(새 플랜) · project_init(추적 초기화, confirm 필수)
스킬 5종 (자동 발동)
oculpm-journal(도구 없을 때 파일 기록 규격) · project-inception(설계) · run-evals(EVALS.md 실행) · self-audit(완료 선언 전 자기 감사) · tdd-workflow(테스트 먼저)
훅 (자동)
세션 시작/종료 이벤트 기록 · 활성 플랜 요약 주입(세션·서브에이전트) · 일지 미작성 세션 감지 + 배달 게이트(코드 변경에 일지가 없으면 세션당 1회 안내) · statusline 배지(옵인: /statusline 에서 hooks/oculpm-statusline.sh 지정)
전체 문서: oculpm.com/plugin
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.
- today Changed b83ba6b479bd
- 5d ago First seen · 32 lines · 35 tokens per session scan A 2153fd519c07
help is a command published in the GitHub repository bunhine0452/Ocul-PM (7 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 534 once invoked, about $0.0002 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 commands, from other repositories
add-agent
引导新增一个 Agent 适配器。用法 /add-agent.
check
跑全套本地校验(前端 lint/test/build + Rust check)。.
mach12:issue-review
Read a GitHub issue and all comments, review the implementation plan, and present findings.
mach12:gh-pr-read
Read a GitHub pull request's title, body, and all top-level PR conversation comments; optionally locate an HTML-marker comment.
search
Search X (Twitter) and the web in real time with Grok, then summarize with sources.
result
Show the final output of a completed Grok job.