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.
git 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/plugins/bunhine0452/ocul-pm/oculpm)<a href="https://agentmods.dev/plugins/bunhine0452/ocul-pm/oculpm"><img src="https://agentmods.dev/badge/plugins/bunhine0452/ocul-pm/oculpm/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/plugins/bunhine0452/ocul-pm/oculpm"><img src="https://agentmods.dev/badge/plugins/bunhine0452/ocul-pm/oculpm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
oculpm 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 3d 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.
What it actually says
{
"name": "oculpm",
"version": "3.13.2",
"description": "Local-first work journal for AI coding agents. Wires a hook bridge (session start/stop, local file append only — no network), MCP tools (journal_write / journal_search / journal_read / plan_status / plan_update / plan_create) that write markdown journals and living plans into your project's .oculpm/, and skills for journaling, project inception, self-audit, evals and TDD. Works only in repos already tracked with .oculpm/; macOS, Linux and Windows (Windows hooks need Git Bash). — ocul-pm 훅 브리지와 oculpm-mcp(구조화 일지/플랜 도구)를 한 번에 구성합니다. .oculpm 이 있는 프로젝트에서만 동작합니다.",
"author": {
"name": "ocul-pm",
"url": "https://oculpm.com"
},
"homepage": "https://oculpm.com",
"repository": "https://github.com/bunhine0452/Ocul-PM",
"license": "MIT",
"keywords": [
"ocul-pm",
"journal",
"planner",
"hooks",
"mcp"
]
}
What it installs
The manifest is a name and a version. 5 skills, 6 commands travel with it, and installing the plugin installs all of them — 468 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill oculpm-journal A 58 tokens
- Skill self-audit A 39 tokens
- Skill project-inception A 85 tokens
- Skill run-evals A 46 tokens
- Skill tdd-workflow A 47 tokens
- Command board A 35 tokens
- Command help A 35 tokens
- Command next A 31 tokens
- Command project_init A 33 tokens
- Command standup A 28 tokens
- Command inception A 31 tokens
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.
- 3d ago Changed ad75ba924c66
- 7d ago Changed fdc1340b37fb
- 10d ago Changed 2497343555b0
- 12d ago Changed 76fc9b94f3d4
- 13d ago Changed 069b30d1017b
- 14d ago Changed e3df3af0ad93
- 16d ago Changed a99b3c652fa4
- 22d ago Changed 31d2b742eab0
- 27d ago Changed fec5a7113f51
- 29d ago First seen · 20 lines scan A ae070b80d9f2
oculpm is a plugin published in the GitHub repository bunhine0452/Ocul-PM (7 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
before-you-build
Pre-build product risk review for founders, product teams, and AI-assisted builders before implementation starts.
rosetta-light
Rosetta for Claude - Software Engineering Accelerator instruction set, workflows, and guardrails. (lightweight: simpler workflows, smaller models).
pad
Talk to your project. Pad is local-first project management for developers and AI agents — this plugin gives Claude Code a conversational Pad skill, typed shortcuts (/pad:status, /pad:capture, /pad:onboard, /pad:connect, /pad:disconnect), a /pad-pane side panel for browsing and updating your workspace, and…
mattpocock-skills
Skills adapted from Matt Pocock's public collection.
shopify-app-builder
Production-focused Shopify app engineering guidance for Gemini CLI.
kelvia
Give Claude a task board it can actually run. Kelvia is a free Kanban board shared by you and your agents: Claude files, triages and moves tasks, logs the time it spent, comments its reasoning, and blocks out your day — and every change is attributed to the agent that made it, so you can review or revert it. Connects…