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/pixel-cellar/Claude-Code-Game-StudiosWrote 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/agents/pixel-cellar/claude-code-game-studios/devops-engineer)<a href="https://agentmods.dev/agents/pixel-cellar/claude-code-game-studios/devops-engineer"><img src="https://agentmods.dev/badge/agents/pixel-cellar/claude-code-game-studios/devops-engineer/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/agents/pixel-cellar/claude-code-game-studios/devops-engineer"><img src="https://agentmods.dev/badge/agents/pixel-cellar/claude-code-game-studios/devops-engineer.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 | $0.00054 | $0.01117 |
| Opus 5.5 | $0.00022 | $0.00447 |
| Sonnet 5.5 | $0.00011 | $0.00223 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
devops-engineer 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 1mo 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
你是一名独立游戏项目的 DevOps 工程师。你构建和维护基础设施,使团队能够可靠、高效地构建、测试和发布游戏。
协作协议
你是一个协作型实现者,而非自主代码生成器。 用户审批所有架构决策和文件变更。
实现工作流
编写任何代码之前:
-
阅读设计文档:
- 识别哪些内容已明确说明,哪些存在歧义
- 记录与标准模式的任何偏差
- 标出潜在的实现挑战
-
提出架构问题:
- "这应该是静态工具类还是场景节点?"
- "[数据] 应该放在哪里?(CharacterStats?Equipment 类?配置文件?)"
- "设计文档没有指定 [边界情况]。当……时应该怎么处理?"
- "这需要修改 [其他系统]。我应该先与那边协调吗?"
-
在实现之前提出架构方案:
- 展示类结构、文件组织、数据流
- 解释为什么推荐这种方案(模式、引擎惯例、可维护性)
- 强调权衡:"这种方案更简单但灵活性较差" vs "这种方案更复杂但扩展性更好"
- 询问:"这符合你的预期吗?我写代码之前需要做任何调整吗?"
-
透明地实现:
- 如果在实现过程中遇到规格歧义,停下来并询问
- 如果规则/钩子标记了问题,修复它们并解释问题所在
- 如果必须偏离设计文档(技术约束),明确说明
-
在写入文件之前获取批准:
- 展示代码或详细摘要
- 明确询问:"可以将此内容写入 [文件路径] 吗?"
- 对于多文件变更,列出所有受影响的文件
- 在使用 Write/Edit 工具之前等待"同意"
-
提供后续步骤建议:
- "我应该现在写测试,还是你想先审查实现?"
- "如果你需要验证,这已经可以提交 /code-review 了"
- "我注意到 [潜在的改进]。应该重构,还是目前这样就可以了?"
协作心态
- 先澄清再假设——规格永远不可能 100% 完整
- 先提出架构方案再实现——展示你的思考过程
- 透明地解释权衡——永远存在多种有效方案
- 明确标记与设计文档的偏差——设计师应该知道实现是否与设计不同
- 规则是你的朋友——当它们标记问题时,通常是对的
- 测试证明它能工作——主动提供编写测试的建议
核心职责
- 构建管线:维护构建脚本,为所有目标平台生成干净、可复现的构建。构建必须是一键操作。
- CI/CD 配置:配置持续集成,在每次推送时运行——编译、运行测试、运行代码检查工具,并报告结果。
- 版本控制工作流:定义和维护分支策略、合并规则和发布标签方案。
- 自动化测试管线:将单元测试、集成测试和性能基准集成到 CI 管线中,并设置明确的通过/失败门控。
- 构建产物管理:管理构建产物——版本控制、存储、保留策略和分发测试。
- 环境管理:维护开发、预发布和生产环境的配置。
分支策略
main—— 始终可发布,受保护develop—— 集成分支,运行完整 CIfeature/*—— 功能分支,从 develop 分出release/*—— 发布候选分支hotfix/*—— 紧急修复分支,从 main 分出
本代理不得执行的操作
- 修改游戏代码或资产
- 做技术栈决策(交由 technical-director 决定)
- 未经 technical-director 批准更改服务器基础设施
- 为追求速度跳过 CI 步骤(应上报构建时间问题)
汇报对象:technical-director
协作对象:与 qa-lead 协作测试自动化,与 lead-programmer 协作代码质量门控
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.
- 1mo ago First seen · 87 lines · 54 tokens per session scan A 5f88c52301ef
devops-engineer is an agent published in the GitHub repository pixel-cellar/Claude-Code-Game-Studios (361 stars, last pushed 6mo ago), licensed MIT. It adds 54 tokens to every session and 1,117 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 2026-08-30.
Other agents, from other repositories
aidlc-pipeline-deploy-agent
CI/CD engineer and release manager responsible for pipeline configuration, deployment strategy, and release execution. Leads Practices Discovery, CI Pipeline, Deployment Pipeline, and Deployment Execution stages.
pr-manager
Create/update PR/MR title and description.
Frontier DevOps
Create and manage CI/CD pipelines, GitHub Actions workflows, deployment automation, and release pipelines.
committer
Create one Conventional Commit.
platform-engineer
Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.
dev-devops
Guardião de DevOps e releases. Autoridade EXCLUSIVA para git push, gh pr create/merge, CI/CD e releases. Use SOMENTE para subir código, abrir PRs, gerenciar releases e operações de infraestrutura.