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 skills/quan0715/open-press/openpress-pluginsnpx skills add quan0715/open-press --skill openpress-pluginsgit clone --depth 1 https://github.com/quan0715/open-pressWrote 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/quan0715/open-press/openpress-plugins)<a href="https://agentmods.dev/skills/quan0715/open-press/openpress-plugins"><img src="https://agentmods.dev/badge/skills/quan0715/open-press/openpress-plugins.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 | $0.00038 | $0.00618 |
| Opus 5 | $0.00019 | $0.00309 |
| Sonnet 5 | $0.00008 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
openpress-plugins 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 4d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenPress Plugins
Manage, recommend, and adapt external specialized skills into OpenPress documents, components, and media.
Workflow
-
Recognize Intent:
- Match user requests (e.g. "畫架構圖", "system diagram", "flowchart", "sequence diagram", "cover design") against triggers in
references/catalog.json.
- Match user requests (e.g. "畫架構圖", "system diagram", "flowchart", "sequence diagram", "cover design") against triggers in
-
Check Readiness & Recommend:
- If installed (
.agents/skills/<id>orskills/<id>exists): invoke the plugin skill directly, then read its matching adapter. - If not installed: present a compact, actionable Recommendation Card in chat:
- If installed (
### 🧩 Recommended Plugin: <Plugin Name>
<Short Description>
- **Source**: `<source>` (<License>)
- **Why**: <Why this plugin fits the user's specific request>
**Options:**
1. **Install & Use**: Follow the short installation note in the matching adapter, then proceed with the generation.
2. **Continue with Native**: Proceed using standard OpenPress basic SVG without installing the plugin.
-
Handle User Response:
- Install & Use: Give the adapter's natural-language installation note, then invoke the plugin and adapt its output.
- Native Fallback: Generate standard basic React SVG figure or table directly without external dependencies.
-
Adapt and Insert:
- Save visual components to
press/<slug>/components/figures/<Name>Figure.tsx(orcomponents/<Name>Figure/index.tsx). - For writing plugins: apply edits directly to the target MDX file.
- Follow
openpress→ Local Review Gate (npm run dev:workspaceornpm run build) to verify layout, pagination, and theming.
- Save visual components to
Responsibility Boundary
openpress-plugins: Recommends external skills based on document authoring needs (e.g. diagrams, posters, writing polish) and provides adapters to convert external skill outputs into OpenPress native components (components/figures/<Name>Figure.tsx).- Workbench Updates (
/workspace/settings): Read-only capability status in the UI with copyable prompts for Agent handoff. - Codex / Claude (Agent): Executes actual remote inspection, dependency upgrades,
skills-lock.jsonhash updates, and verification.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 52 lines · 38 tokens per session scan A 941a46541e2a
openpress-plugins is a skill published in the GitHub repository quan0715/open-press (14 stars, last pushed 6d ago), licensed MIT. It adds 38 tokens to every session and 618 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 2026-08-30.
Other skills, from other repositories
anvil-batch-articles
从用户给的关键词清单批量生成一批符合 AnvilWiki schema 的 MDX 内页：按搜索意图归类 → 生成 new-posts.csv → pnpm bulk-new-posts 批量建草稿 → 按统一提示词模板逐篇填充 → 全批验收。触发词：批量写文章 / 一次生成一堆攻略 / 关键词清单生成页面 / batch articles。.
kb-import
Import knowledge from existing documents into structured KB entries. Reads source documents (Markdown, PDF, DOCX, plain text), extracts key information, and creates properly formatted KB entries with YAML frontmatter.
explain-document
This skill should be used when the user says "explain this document", "interpret this file", "what does this plan commit me to", "what does this ADR say", "interpret this architecture doc", "what does this AI-generated plan actually mean", "decompile this doc", "what's this file saying", "explain this to me in plain…
usage-policy-writer
Generate a human-facing AI usage policy with approved tools, data classification, risk model explanations, and exception processes — saved to $HOME/.ai-first-kit/. Produces a policy document for HUMANS (not agents) that explains what AI tools are approved, what data can be used with AI, and the reasoning behind each…
accounting-workflow
End-to-end Malaysian accounting engagement workflow. Takes a client folder and produces accrual-basis financial statements (Excel working papers + PDF) compliant with MPERS / MFRS / ITA 1967. Covers Sole Proprietor, Partnership, Sdn Bhd, Berhad, and NGO. USE THIS SKILL when the user wants to: Start or continue an…
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…