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 skills add bunhine0452/Ocul-PM --skill oculpm-journalgit 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/skills/bunhine0452/ocul-pm/oculpm-journal)<a href="https://agentmods.dev/skills/bunhine0452/ocul-pm/oculpm-journal"><img src="https://agentmods.dev/badge/skills/bunhine0452/ocul-pm/oculpm-journal/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/skills/bunhine0452/ocul-pm/oculpm-journal"><img src="https://agentmods.dev/badge/skills/bunhine0452/ocul-pm/oculpm-journal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.01283 |
| Opus 5 | $0.00029 | $0.00642 |
| Sonnet 5 | $0.00012 | $0.00257 |
| Haiku 4.5 | $0.00006 | $0.00128 |
Grade A, and why
oculpm-journal 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 6d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ocul-pm 기록 규격 (풀 스펙)
MCP 도구가 보이면 이 스킬 대신 도구를 쓴다 — journal_write / plan_status /
plan_update 가 경로·파일명·frontmatter 규격을 서버에서 보장한다. 아래는 도구가
없을 때 파일을 직접 쓰는 규격이다.
plan_update는base_hash가 필수다 — 먼저plan_status로 그 플랜의hash를 읽고 그대로 넘긴다. 병렬 세션이 같은 플랜을 고칠 때 한쪽 변경이 조용히 사라지는 것을 막는 장치다. 어긋나면 아무것도 쓰지 않고 현재 hash 를 담은 오류가 오니, 다시 읽어 판단한 뒤 새 hash 로 재호출한다.
1. 작업 일지
경로: .oculpm/journal/{YYYYMMDD}/{TypeFolder}/{HHMM}_{type}_{slug}.md
TypeFolder=Bugs|Features_to_add|Errors|Refactors|Chorestype∈ {bug,feature,error,refactor,chore},slug= ASCII kebab-case ≤40자- 하나의 파일에 두 개 이상의 작업을 묶지 말 것. 기존 일지 수정 금지 (새 파일 +
related링크).
frontmatter (8개 필수 — 자주 틀리는 3가지: ① created_at 은 +09:00 형태 tz offset 필수,
② agent 는 id/version 키를 가진 mapping, ③ files_touched[].op 은
create|update|delete|rename|correct enum 만):
---
schema_version: 1
type: bug
slug: short-kebab-slug
status: done # planned | in_progress | done | abandoned
created_at: "2026-07-31T14:03:00+09:00"
session_id: "manual-<workday>-HHMMSS"
agent: { id: claude-code, version: "모델명" }
language: ko
verified_by_user: false
files_touched: [{ path: src/x.rs, op: update }]
related: []
tags: []
---
본문: 첫 줄 [x] 제목 체크박스. 타입별 강제 헤더 — bug/error: ## 발생 원인 →
## 해결 방법, feature: ## 추가 기능 → ## 동작 흐름, refactor: ## 동기 →
## 변경 요약. 공통 끝: ## 검증 (필수, 1~3줄), ## 메모 (선택).
학습 품질 (growth-log 규율): 일지는 성과 나열이 아니라 다음 세션이 헛수고를
안 하게 하는 기록이다 — 실패한 접근·막다른 길·의외였던 사실을 성공보다 우선
기록한다 ("X 를 시도했지만 Y 라서 안 됨"이 "X 완료"보다 값지다). 같은 실패를
반복하지 않도록 ## 메모 에 다음 독자를 위한 학습 1줄을 남긴다.
금지: .oculpm/index/** 쓰기, secrets/API key 포함, 기존 일지 수정.
2. 플래너 갱신 (일지 직후)
.oculpm/planner/*.md 의 대응 항목이 있으면: ① 상태 글리프 변경 — [ ] 할일 ·
[~] 진행중 · [x] 완료 · [!] 막힘 · [>] 이월 · [-] 폐기, ② 하단 managed
block 에 한 줄 append (기존 행 수정 금지):
<!-- oculpm:plan-log begin v1 -->
| 시각 | 항목 | 에이전트 | 변화 | 일지 | 메모 |
|---|---|---|---|---|---|
| 2026-07-31T14:03:00+09:00 | #item-id | claude-code | ~→x | journal/…/x.md | |
<!-- oculpm:plan-log end -->
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.
- 6d ago Changed · +5 lines b4a52e05acfe
- 11d ago First seen · 78 lines · 58 tokens per session scan A 8a311c20e1fc
oculpm-journal is a skill published in the GitHub repository bunhine0452/Ocul-PM (7 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 1,283 once invoked, about $0.0003 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 skills, from other repositories
general
Handle everyday conversation, answer questions, manage files, take notes, run scripts, and maintain persistent memory across sessions. Use when the user asks a general question, requests file operations, wants to brainstorm ideas, needs to-do tracking, asks you to remember something, or requests skill search and…
message-push
Send proactive messages to IM groups or individual users via the gateway Send API. Use when the user says to send, post, notify, forward, or tell someone a message on Feishu, Slack, Telegram, Discord, DingTalk, or WeCom.
task-manager
Creates and manages scheduled tasks, cron jobs, recurring reminders, and timers via the Task HTTP API. Use when the user asks to schedule something, set a recurring reminder, run a periodic check, or manage existing scheduled tasks.
meeting
Meeting notes assistant — organizes transcripts into structured minutes, extracts action items, and tracks attendee decisions. Use when the user asks to summarize a meeting, take meeting notes, write up minutes, create a meeting recap, list attendees, or extract action items from a call.
agentbro-pr-merge
Use when reviewing, fixing CI for, approving workflows for, or merging AgentBro pull requests into dev/main, especially external contributor PRs where contributor attribution matters.
cursor-delegate
Delegate bounded light-to-medium implementation, investigation, documentation, configuration, testing, and tooling work to Cursor Bridge after the primary agent owns direction and risk boundaries. Also use when the user explicitly asks to create, keep, continue, inspect, or close the same Cursor execution session…