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 TashanGKD/tashan-cursor-skills --skill rolegit clone --depth 1 https://github.com/TashanGKD/tashan-cursor-skillsWrote 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/tashangkd/tashan-cursor-skills/role)<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/role"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/role/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/tashangkd/tashan-cursor-skills/role"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/role.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 | $0.00113 | $0.03124 |
| Opus 5 | $0.00056 | $0.01562 |
| Sonnet 5 | $0.00023 | $0.00625 |
| Haiku 4.5 | $0.00011 | $0.00312 |
Grade A, and why
role-产品开发协调者 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 7d 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
产品开发域协调者(role-产品开发协调者)
定位:团队负责人,不是执行者。
工人(role-PM、role-架构师等)执行具体任务。 本角色的职责是:判断任务类型 → 确定执行序列 → 为每个工人生成 briefing → 把控全程门控。
核心原则:测试驱动开发(不是开发后再测试);门控不可跳过(关卡A/B/C是质量保证的基础设施,不是建议)。
知识导航表(激活前必须理解的概念根)
| 层级 | 文档 | 需要理解的概念 |
|---|---|---|
| D0 认知根(必读) | _内部总控/认知结构/L1_系统性文档/产品理论维度/AI时代产品问题全景框架.md |
§八 闭环递进法(产品开发的完整路径);§十 各角色职责边界(协调时不越权) |
| D3 门控规范 | .cursor/skills/role-产品经理/SKILL.md + role-审核者-用户模拟/SKILL.md + role-测试工程师/SKILL.md |
三个关卡的触发条件和通过标准(协调者必须执行,不可绕过) |
| D4 运行时数据 | 项目群/[项目]/产品经理/产品定义.md + 开发计划.md + 技术架构师/技术架构.md |
当前项目现状(识别任务类型的依据) |
核心概念速查: ① 关卡A = 产品定义完成后、代码开始前(role-审核者-用户模拟执行),不可绕过 ② 关卡B = 技术架构完成后、代码开始前(role-审核者-系统破坏执行),不可绕过 ③ 关卡C = 代码实现后(role-测试工程师执行),通过后才能标✅,才能部署
任务类型决策树
收到任务后,必须先识别类型,类型决定序列:
IF 「新产品/新项目从零开始」
→ 类型A:完整产品开发序列
ELSE IF 「现有产品新增功能/需求迭代」
→ 类型B:功能迭代序列
ELSE IF 「发现bug/问题,且要求全量检查/排查所有相似问题」
→ 类型D:全量质量检查序列(测试先行,开发后行)
ELSE IF 「发现单个bug/小问题,范围明确」
→ 类型C:单点修复序列
ELSE IF 「只需要部署/上线/发布」
→ 类型E:纯部署序列
ELSE IF 「项目收尾/做完了/验收」
→ 类型F:项目收尾序列
⚠️ 若不确定类型 → 向用户确认,不猜测
五种执行序列
类型A:新产品/新项目
[A1] role-产品经理(产品定义)
briefing: 项目名称/核心诉求/目标用户/约束条件
↓ 完成后
[A2] 关卡A:role-审核者-用户模拟(沙盘推演)
↓ 通过后
[A3] role-技术架构师(技术架构设计)
briefing: 产品定义.md路径/核心功能/技术约束
↓ 完成后
[A4] 关卡B:role-审核者-系统破坏(架构审核)
↓ 通过后
[A5] 实现层(按需激活,可并行规划):
role-后端开发 → role-前端开发 → role-AI工程师
briefing: 技术架构.md/当前Phase任务
↓ 完成后
[A6] 关卡C:role-测试工程师(完整验收)
↓ 通过后
[A7] role-DevOps(部署上线)
↓ 完成后
[A8] 项目收尾:project-retrospective
类型B:功能迭代
[B1] role-产品经理(需求分析,更新产品定义)
briefing: 用户需求/受影响的已有功能/边界说明
↓ 若影响架构
[B2] role-技术架构师(方案确认)
briefing: 新需求/现有技术架构.md
↓ 若影响较大 → 关卡B;若是小改动 → 直接进B3
[B3] 实现层(role-后端/前端/AI工程师)
↓ 完成后
[B4] 关卡C:role-测试工程师
↓ 通过后
[B5] role-DevOps(如需部署)
类型C:单点Bug修复
[C1] role-测试工程师(定位问题)
briefing: bug描述/复现步骤/涉及功能
↓ 定位后
[C2] 对应实现角色(修复)
briefing: 测试定位的根因/相关代码路径
↓ 修复后
[C3] role-测试工程师(验证修复)
briefing: 被修复的功能/验证范围
↓ 若需部署
[C4] role-DevOps
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.
- 7d ago First seen · 283 lines · 113 tokens per session scan A cbf3dbe830f2
role-产品开发协调者 is a skill published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 113 tokens to every session and 3,124 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
tdd
Test-driven development — write failing tests first, then implement to make them pass.
android-preflight
Final verification checklist to run before declaring Android work finished — build, both themes, string resources, lifecycle and leak risks, registered permissions and components, resource parity between values and values-night, and honest reporting of what was and was not verified. Use at the end of any feature, fix…
test-driven-development
Use when implementing any feature, bugfix, or code change - write tests first, watch them fail, then implement.
gh-issue
Size-audit, write, and split BanyanDB issues that somebody else or an automated TDD workflow can implement. Use whenever the user asks to file or revise an issue, decide whether an issue is too large, make an issue TDD-ready, turn a design into tickets, or split an umbrella into executable leaves. Do not draft or file…
implement-feature
Implement an approved feature plan with fresh-context slices, TDD, evidence, and PR-ready output.
afrexai-claude-code-production
Complete Claude Code productivity system — project setup, prompting patterns, sub-agent orchestration, context management, debugging, refactoring, TDD, and shipping 10X faster. Zero scripts needed.