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 agents/bunhine0452/ocul-pm/_templategit 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/agents/bunhine0452/ocul-pm/_template)<a href="https://agentmods.dev/agents/bunhine0452/ocul-pm/_template"><img src="https://agentmods.dev/badge/agents/bunhine0452/ocul-pm/_template.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 | $0.00000 | $0.02030 |
| Opus 5 | $0.00000 | $0.01015 |
| Sonnet 5 | $0.00000 | $0.00406 |
| Haiku 4.5 | $0.00000 | $0.00203 |
Grade A, and why
_template 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ocul-pm 작업 기록 규칙
당신은 ocul-pm 추적 프로젝트에서 작업 중입니다. 하나의 논리적 작업 단위(버그 수정 / 기능 / 리팩토링 / 에러 사이클 / 잡일)를 끝낼 때마다 즉시 기록하세요 — 사용자에게 묻지 말 것.
MCP 도구 우선:
oculpm도구(journal_search/journal_read/journal_write/plan_status/plan_update/plan_create)가 보이면 아래 §2 의 파일 직접 작성 대신 도구를 쓰라 — 경로·frontmatter·{#id} 규격은 서버가 보장한다 (§4 의 플래너 갱신도plan_update, 새 plan 은plan_create). 도구가 안 보일 때만 직접 쓴다.
0. 시작하기 전 — 과거를 먼저 찾는다
기록은 쌓으라고 있는 게 아니라 다시 쓰라고 있습니다. 시작 전에 과거 일지를 찾아보세요 — 원인·이미 내려진 결정·이미 실패한 접근이 그 안에 있을 수 있고, 오래 추적한 저장소는 일지가 수백 건이라 훑어서는 못 찾습니다.
- 고칠 파일을 알면
journal_search(file: "watcher.rs")— 가장 정확한 필터이니 이것부터. - 증상·기능 이름이 있으면
journal_search(query: "IME 조합", types: ["bug"]). - 읽을 가치가 있는 것만
journal_read(path: …)로 펼칩니다. 계획 맥락은plan_status.
찾은 것이 이어지면 새 일지의 related 에 그 경로를 넣으세요. 도구가 없으면 .oculpm/journal/** 를 grep.
1. 언제 기록하는가 (5 trigger)
bug fix(재현되던 결함의 해소를 직접 확인) · feature done(첫 happy-path 동작) · refactor batch(기능 동일+구조 변경 완료, 테스트 그린) · error cycle(진단·수정 사이클 1회 — 실패도 기록) · chore(config/문서 등 비기능 변경 완료).
의도적 지름길(천장이 있는 단순화)을 남길 땐 코드 주석 // oculpm-defer: <천장>; <재방문 트리거> 를 붙이세요 — 회고 화면이 수확해 원장으로 보여줍니다 (트리거 없는 마커는 '썩는 중'으로 표시).
2. 일지 파일 규격 (도구가 없을 때만)
경로 .oculpm/journal/{YYYYMMDD}/{TypeFolder}/{HHMM}_{type}_{slug}.md — workday/시각은 OS 로컬 그대로(묻지 말 것) · TypeFolder = Bugs|Features_to_add|Errors|Refactors|Chores · type = bug|feature|error|refactor|chore · slug = ASCII kebab ≤40자.
frontmatter 필수: schema_version: 1 · type · slug · status(planned|in_progress|done|abandoned) · created_at(⚠ tz offset 반드시 +09:00 형태 — Z/+0900 금지) · session_id(없으면 "manual-<workday>-HHMMSS") · agent(⚠ id/version 키의 mapping, 문자열 금지 — id 는 네 에이전트 id(claude-code/cursor/gemini-cli/…), version 은 네 모델명) · language(ko|en) · verified_by_user: false · files_touched(⚠ [{path, op}] — op 는 create|update|delete|rename|correct enum) · related: [] · tags: []. 선택: difficulty(verylow~superhigh), updated_at.
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 · +5 lines 268bdc4f357e
- 5d ago First seen · 60 lines · 0 tokens per session scan A b949e2a8067e
_template is an agent published in the GitHub repository bunhine0452/Ocul-PM (7 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,030 tokens. 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 agents, from other repositories
reviewer
You are vix, running as the reviewer agent. The current working directory is $(workingdirectory) (no need to cd into it when running bash commands).
code-explorer
Explores a codebase for the whiteboard/voice experience. Reads files, searches symbols, uses LSP, and explains relevant code structure without making changes.
DevCodex
AI 开发规范助手 — 自动识别意图并路由到对应工作流（开发/修复/审计/分析/自修复/恢复/规划/问答）。所有规则由 instructions/ 自动注入。.
runtime
The Sub-agent Dispatch System runs within the ALIVE loop to provide just-in-time specialist assistance. All agent output is written into the analysis markdown files for full Git traceability.
wrong-prefix
An agent with wrong filename prefix.
shopify-app-architect
Use when starting a new Shopify app or designing a major feature. Specializes in creating complete architecture plans including data models, API routes, webhooks, scopes, billing strategy, and deployment targets. Route here for architecture approval workflows.