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 skills add lazysheep-z/apdr-product-design-runtime --skill operator-preferencegit clone --depth 1 https://github.com/lazysheep-z/apdr-product-design-runtimeWrote 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/lazysheep-z/apdr-product-design-runtime/operator-preference)<a href="https://agentmods.dev/skills/lazysheep-z/apdr-product-design-runtime/operator-preference"><img src="https://agentmods.dev/badge/skills/lazysheep-z/apdr-product-design-runtime/operator-preference/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/skills/lazysheep-z/apdr-product-design-runtime/operator-preference"><img src="https://agentmods.dev/badge/skills/lazysheep-z/apdr-product-design-runtime/operator-preference.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 | $0.00061 | $0.00991 |
| Opus 5.5 | $0.00024 | $0.00396 |
| Sonnet 5.5 | $0.00012 | $0.00198 |
| Haiku 4.5 | $0.00006 | $0.00099 |
Grade A, and why
apdr-operator-preference 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operator Preference (APDR 横切)
在 intake / requirements / PRD / UI / design_review / frontend 等人机门禁多轮对话中使用。 不替代产品 personas;只优化「你怎么跟 Agent 协作」。
MCP(优先)
get_operator_preference { project_id }
set_operator_preference { project_id, preference: { ...partial } }
get_next_action 会附带偏好与「交付护栏」。引擎会按偏好自动跳过阶段。
When
- 新项目首次 intake:用 2–3 个短问题收集偏好,经 MCP 写入
- 用户说「简洁一点 / 只改文案 / 不要代码只要飞书文档 / 改现有原型」:立刻
set_operator_preference - 每个阶段开始:先
get_operator_preference
Persist
- MCP →
projects/{id}/operator-preference.json(gitignore,不进公开仓库) - 关键字段镜像到
meta.json:deliveryTarget/prototypeMode/taskMode
隐私:只存协作枚举;禁止姓名、邮箱、手机、飞书 open_id、租户域名、本机绝对路径。写入时会自动 [redacted]。
Schema
{
"communicationDensity": "concise|balanced|thorough",
"clarifyFirst": true,
"gateStyle": "strict|default|fast-forward-optional",
"feedbackStyle": "summary-only|inline-comments|rewrite-whole",
"language": "zh|en",
"wireframeFidelity": "low|mid",
"revisionMode": "patch|restage",
"prototypeMode": "greenfield|incremental",
"docOnlyGuard": true,
"deliveryMode": "preview|offline-html|both|none",
"deliveryTarget": "code|feishu-doc|both",
"taskMode": "full|copy_only|patch_ui",
"previewPort": 5180,
"previewHostLan": true,
"notes": []
}
推荐默认值
中文 / concise / strict / patch / incremental / docOnlyGuard / deliveryMode=both / deliveryTarget=code / taskMode=full / previewHostLan=true。
路线跳过(引擎)
| 设置 | 跳过阶段 |
|---|---|
deliveryTarget=feishu-doc |
user_flows → code_intelligence(PRD 后直接 handoff) |
taskMode=copy_only |
UX/UI/设计审查/后端/图谱(Brief 后可进 frontend 文案改) |
prototypeMode=incremental 或 taskMode=patch_ui |
可选 UX:flows/IA/wireframes/ui/design_review |
Intake 最多 2–3 题
- 从零新建,还是改现有原型?(→ prototypeMode / taskMode)
- 要代码、只要飞书/文档,还是都要?(→ deliveryTarget)
- 是否需要后端? / 只要改文案?(→ includeBackend / taskMode=copy_only)
Apply rules
| Preference | Agent behavior |
|---|---|
concise |
每轮 ≤5 要点;中文短句 |
strict |
未明确「批准」不 approve |
patch |
只改被点名段落 |
incremental / patch_ui |
既有代码上改;跳过可选 UX |
copy_only / docOnlyGuard |
只改文案;改字段前先列影响点 |
feishu-doc |
文档交付;跳过线框→代码 |
offline-html / preview |
按交付护栏校验 pack:single 与 LAN 预览 |
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 · -5 lines e91085daf72f
- 27d ago First seen · 98 lines · 61 tokens per session scan A 29c424a5bce4
apdr-operator-preference is a skill published in the GitHub repository lazysheep-z/apdr-product-design-runtime (3 stars, last pushed 3d ago), licensed MIT. It adds 61 tokens to every session and 991 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 2026-09-21.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…