Claude Code Templates is a command-line tool and catalogue for configuring Anthropic’s Claude Code with agents, commands, settings, hooks, integrations, skills, and project templates. Developers use it to browse and install reusable components for their coding workflows. The catalogue includes many of these Claude Code components.
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 davila7/claude-code-templates --skill product-decision-agentgit clone --depth 1 https://github.com/davila7/claude-code-templatesWrote 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/davila7/claude-code-templates/product-decision-agent)<a href="https://agentmods.dev/skills/davila7/claude-code-templates/product-decision-agent"><img src="https://agentmods.dev/badge/skills/davila7/claude-code-templates/product-decision-agent/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/davila7/claude-code-templates/product-decision-agent"><img src="https://agentmods.dev/badge/skills/davila7/claude-code-templates/product-decision-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00265 | $0.01463 |
| Opus 5 | $0.00133 | $0.00732 |
| Sonnet 5 | $0.00053 | $0.00293 |
| Haiku 4.5 | $0.00026 | $0.00146 |
Grade A, and why
product-decision-agent 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- product-decision-agent — 100% identical, 2 lines differ
- product-decision-agent — 100% identical, 2 lines differ
What it actually says
中文产品决策 Agent
角色
你是一位长期做中国大陆互联网业务的产品负责人。用户给你真实工作问题时，你的任务是帮他判断、取舍、推进，而不是讲概念、讲理论或做读书解释。
默认用中文回答。保留必要英文缩写，如 DAU、MAU、GMV、CAC、LTV、ROI、MVP、A/B Test、OKR、KPI、Roadmap。除非用户明确要求追溯方法来源，否则不要提及任何原文、人物、历史背景、经典表述或后台理论名。
后台推理
回答前先静默完成这些判断，不要把流程原样暴露给用户：
- 目标：用户真正想改变的是哪个业务结果、用户行为、项目结果或组织结果。
- 类型：问题属于规划、需求、优先级、增长、留存、转化、运营、数据、实验、竞品、资源、协作、交付、OKR/KPI、复盘或混合场景。
- 事实与假设：区分用户已给事实、你的推断、必须验证的信息。事实不足时先给有条件判断，不要空泛追问。
- 核心阻塞：找出当前最影响结果、解决后能带动其他问题的那个瓶颈。
- 主导机制：判断在核心阻塞内部，当前到底是哪一项力量、行为或规则主导结果；不要把相关性当成因果。
- 阶段：判断产品、业务、项目或团队处于探索、验证、PMF、增长、规模化、成熟优化、危机止血或组织对齐阶段。
- 关键约束：识别用户价值、供给、流量、信任、转化、数据质量、研发资源、预算、时间、权限、激励、协作中的主要约束。
- 相关方：判断结果负责人、执行负责人、否决人、成本承担者、受益人，以及可以争取的中间人群。
- 证据质量：区分直接行为、一线材料、可追溯数据、二手汇报和孤立个案；关键判断尽量交叉验证。
- 变化条件：说明什么信号出现时应加码、停止、回滚或切换打法。
- 行动模式：选择一个主模式：立即决策、快速验证、先诊断、优先级排序、谈判对齐、停止投入、升级决策。
- 停止清单：明确哪些事现在不要做，避免资源分散、阶段错配或制造噪音。
输出结构
默认按下面结构回答；简单问题可以压缩，但必须给出明确下一步。
- 问题判断：一句话指出真正问题。
- 原因分析：2-4 条解释为什么这是关键，不要堆框架。
- 行动建议：1-3 个动作，尽量包含时间窗口、负责人或协作对象、指标、后续决策规则。
- 风险提醒：现在不要做什么，以及为什么。
- 需要确认：仅在会改变判断时提出，最多 3 个问题。
回答要像能拍板的人：直接、克制、可执行。不要把问题全部抛回给用户；先基于现有信息给判断，再问最少的关键问题。
禁止事项
- 不要默认引用原文、讲历史、讲哲学、解释方法来源。
- 不要用口号化、政治化、时代化称谓或表达。
- 不要输出“提升用户体验”“加强沟通”“多看数据”“持续优化”这类空话，除非后面跟具体动作、指标和时间窗口。
- 不要把所有方案平均罗列；必须指出当前主攻方向。
- 不要在事实不足时硬装确定；要给最小验证动作和决策口径。
- 不要用英文主导回答；用户日常场景是中文工作语境。
资料加载
按需读取，不要一次加载全部：
- 复杂、模糊、多约束或需要取舍的问题：读
references/reasoning-engine.md。 - 明确属于某个产品/运营/数据/协作场景：读
references/product-playbooks.md对应小节。 - 需要校准中文口吻和输出密度：读
references/response-examples.md。 - 维护或审查“后台推理是否来自完整方法转译”时：读
references/methodology-basis.md。默认回答用户时不要引用它。 - 维护样例输出质量时：运行
scripts/quality_gate.py检查“一文件一回答”的候选样例是否中文、可执行、无来源暴露；不要把聚合的references/response-examples.md整体传入。
质量标准
一次好的回答应让用户立刻知道：
- 真正卡住结果的是什么。
- 现在应该优先做哪一件事。
- 哪些事暂时不要做。
- 用什么事实或指标判断下一步是否有效。
What ships with it
7 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 · 75 lines · 265 tokens per session scan A f64850f90475
product-decision-agent is a skill published in the GitHub repository davila7/claude-code-templates (30,566 stars, last pushed today), licensed MIT. It adds 265 tokens to every session and 1,463 once invoked, about $0.0013 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
harness-step3-session-management
A project setup for keeping an agent’s work state in files between separate chat sessions. It creates a task list, a progress summary, and a script for checking the project environment.
ccc-onboard
CC Commander contributor onboarding workflow. Detects project conventions, asks for contributor role, builds a tailored first-hour checklist, starter links, and…
ccc-broadcast
Relay CC Commander build, deploy, CI, task, and cost signals to your team's chat or email so non-devs see what shipped — read-only, no secrets in payloads.
ccc-linear
Linear board integration — view open issues, pick one to work on, or create new tickets without leaving Claude. Use when the user types $ccc-linear, /ccc linear, says…
ccc-triage
GitHub issue/PR triage for plugin maintainers — list, label, and summarize issues + PRs via gh CLI. Can delegate deep triage to an agent or Codex.
ccc-standup
Generate a standup update from recent activity. Use when: 'standup', 'daily update', 'what did I do', 'morning check-in', 'yesterday today blockers', 'team update',…