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/thenw-123/CO-WPSpptWrote 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/rules/thenw-123/co-wpsppt/wps-ppt-pipeline)<a href="https://agentmods.dev/rules/thenw-123/co-wpsppt/wps-ppt-pipeline"><img src="https://agentmods.dev/badge/rules/thenw-123/co-wpsppt/wps-ppt-pipeline/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/rules/thenw-123/co-wpsppt/wps-ppt-pipeline"><img src="https://agentmods.dev/badge/rules/thenw-123/co-wpsppt/wps-ppt-pipeline.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00039 | $0.00545 |
| Opus 5.5 | $0.00016 | $0.00218 |
| Sonnet 5.5 | $0.00008 | $0.00109 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
wps-ppt-pipeline 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 2mo 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
WPS 演示自动化（OpenClaw + COM）
用户要做 PPT / 演示 / WPS 汇报 时：走 JSON spec → wps_dispatch → COM，不要默认 python-pptx 或 Markdown 假装幻灯片。整体数据流见仓库 README.md 里的 「核心逻辑」。
项目位置
仓库根（与 manifest.json、tools/ 同级）。
Cursor 侧
- skills/drive-wps-ppt/SKILL.md；答辩类还须 Skill 里的生成与视觉 QC 约定。
- 已接 Gateway MCP：
openclaw_discover有wps-ppt→openclaw_invoke（action+args_json）。无工具则网关加载 manifest.json，或改 tools/wps_dispatch.ps1。详见 docs/MCP-OpenClaw与wps-ppt.md。 - 成稿优先
run-spec（specPath或内联spec）；叙事版式见specs/narrative-layouts-demo.json。默认校验；大稿可先validate-spec；环境用doctor。 - 边做边改：
new→add-slide/set-text/set-notes→save。
参数约定
- 所有脚本从 stdout 输出一行 JSON：
{"ok":true,"data":{...}}或{"ok":false,"error":"...","code":"..."}；失败时若有data.errors（校验）一并交给用户。 - 可通过环境变量
OC_ARGS_JSON传入与args_json相同的 JSON 字符串。 - 会话文件：
logs/wps-session.json（当前绑定的presentationPath）。
安全
- 不要用
exec跑不可信脚本；exec仅允许项目内的.ps1路径。
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.
- 2mo ago First seen · 30 lines · 39 tokens per session scan A 35475db3c6a5
wps-ppt-pipeline is a cursor rule published in the GitHub repository thenw-123/CO-WPSppt (2 stars, last pushed 6mo ago), licensed MIT. It adds 39 tokens to every session and 545 once invoked, about $0.0002 per session on Opus 5.5. 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 cursor rules, from other repositories
kotlin-springboot-rules
A set of coding rules for Kotlin applications built with Spring Boot, a Java-based framework for web services. It covers project layout, naming, Kotlin style, and common design patterns.
mobx-react-lite-usage
A set of rules for connecting MobX to React function components through mobx-react-lite, a library that makes components observe MobX state.
typescript-code-generation-rules
A set of rules for writing React components in Next.js 14 with TypeScript, including typed props, function components, and export conventions.
react-chakra-ui---typescript-usage
Guidance for using TypeScript with Chakra UI components in React. It covers typed component props, custom themes, editor support, and avoiding the unsafe any type.
matplotlib-visualization
A set of Python guidelines for creating charts with Matplotlib, a library for displaying data visually. It covers basic charts, including scatter plots, line charts, histograms, box plots, and multi-chart layouts.
springboot-jpa-best-practices
A set of Chinese-language rules for structuring Java Spring Boot applications that use JPA, a library for database access.