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/coffeecheese/easy-prd-testing/xmind-exportnpx skills add CoffeeCheese/easy-prd-testing --skill xmind-exportgit clone --depth 1 https://github.com/CoffeeCheese/easy-prd-testingWrote 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/coffeecheese/easy-prd-testing/xmind-export)<a href="https://agentmods.dev/skills/coffeecheese/easy-prd-testing/xmind-export"><img src="https://agentmods.dev/badge/skills/coffeecheese/easy-prd-testing/xmind-export.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 5.1 | $0.00084 | $0.00705 |
| Opus 5 | $0.00042 | $0.00352 |
| Sonnet 5 | $0.00017 | $0.00141 |
| Haiku 4.5 | $0.00008 | $0.00071 |
Grade A, and why
xmind-export 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 5d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
XMind Test-Case Export
Goal
Create a native XMind 2020+ review view while keeping the source Markdown authoritative and read-only.
Locate the source
Accept any of these as --input:
- An absolute or relative Markdown file path.
- A module directory containing
02-测试用例.md. - A directory containing exactly one recognizable test-case Markdown file.
Prefer 02-测试用例.md when present. If a directory contains multiple recognizable candidates, ask the user to select one. Write the XMind beside the selected source with the same basename.
Export
Require Node.js 18 or newer. If it is missing, ask the user to install it; never install it automatically.
Run:
node <skill-dir>/scripts/export_test_cases.mjs \
--input "/path/or/module-directory"
Interpret the JSON status:
created: report the output path, case count, and warnings.updated: report the output path, update reason, optional backup path, and warnings.up-to-date: report that the existing XMind already matches the source.error: report the actionable errors. Do not claim an output was generated.
Do not ask for overwrite confirmation. Managed XMind files update atomically when the source changes. Before replacing an unknown same-name XMind, the exporter preserves it as .bak, .bak.1, and so on. --force remains accepted only for backward compatibility.
Compatibility behavior
- Scan and merge all recognizable Markdown test-case tables.
- Recognize canonical and legacy aliases such as
用例ID,操作/校验,校验点, and预期. - Infer priority from the explicit column, then section heading, then case ID.
- Keep
P0-P3branches and add未分级only when needed. - Generate missing IDs, fill missing content with
待补充, default yes/no flags to否, and label affected cases待补充. - Treat
01-模块拆解.mdandF-xxxtraceability as optional enhancements. - Return skipped tables, defaults, conflicts, and unmatched feature references as warnings without blocking export.
Stop only when the input cannot be resolved uniquely, Node.js is unavailable, no recognizable Markdown test-case table exists, or the generated XMind fails structural validation.
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.
- 5d ago First seen · 66 lines · 84 tokens per session scan A 76742ba2497b
xmind-export is a skill published in the GitHub repository CoffeeCheese/easy-prd-testing (2 stars, last pushed 24d ago), licensed MIT. It adds 84 tokens to every session and 705 once invoked, about $0.0004 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
draft-openspec-docs
Collaborative page-drafting mode for the OpenSpec docs. Builds a scratch plan inside the target page (purpose, structure, numbered draft steps), iterates on it with the user, then drafts one section per approved step and cleans up after itself. Use when a page needs a from-scratch rewrite or a new page is being shaped…
html-resume
Turn resumes exported from job platforms, existing PDFs, or career notes into independently editable, recruiter-friendly HTML with exact A4 PDF output. Use for resumes, CVs, executive profiles, professional biographies, and portfolio summaries that need Chinese-English translation or same-language rewriting, factual…
obsidian-history-check
用 Obsidian 官方 CLI 做文档历史与 diff 的只读检查。默认不执行 history:restore——恢复必须单独确认。.
obsidian-link-audit
用 Obsidian 官方 CLI 做链接、反链、坏链与孤岛文档审计——改文档前查谁引用了它，改完后确认没留下断链。CLI 不可用时 fallback 到 rg/Read。.
wechat-daily-report-skill
生成微信群聊日报。优先用 jackwener/wx-cli 获取本地微信聊天记录，再输出新版日报 HTML 和 PNG，包含今日剧情、聊天气泡、资料收纳、问答、成员观察和成员过滤。.
qa-audit
QA 审计 — 跑全量文档质量检查,按 P0/P1/P2 严重度分级输出审计报告。设计完成、代码交接前调用本 skill,作为进入实施的最后一道硬门控,确保 P0=0 才放行。.