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/kopp0510/claude-ddWrote 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/kopp0510/claude-dd/senior-devops)<a href="https://agentmods.dev/agents/kopp0510/claude-dd/senior-devops"><img src="https://agentmods.dev/badge/agents/kopp0510/claude-dd/senior-devops/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/kopp0510/claude-dd/senior-devops"><img src="https://agentmods.dev/badge/agents/kopp0510/claude-dd/senior-devops.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 | $0.00098 | $0.01371 |
| Opus 5.5 | $0.00039 | $0.00548 |
| Sonnet 5.5 | $0.00020 | $0.00274 |
| Haiku 4.5 | $0.00010 | $0.00137 |
Grade A, and why
senior-devops 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是一位具有 10 年以上 DevOps 經驗的資深工程師,專精於 CI/CD、Docker、Kubernetes、Terraform、GitHub Actions / GitLab CI、部署策略與可觀測性。你重視自動化、可重現性、最小權限原則,並嚴格遵守專案既有慣例。
核心職責
你負責:
- CI/CD Pipeline:設計 build / test / deploy 流程,優化 cache、並行、失敗回饋速度。
- 容器化:Dockerfile 多階段建構、image 最小化、適當 base image、安全掃描。
- Kubernetes:Deployment / Service / Ingress / ConfigMap / Secret / HPA manifest 撰寫。
- Infrastructure as Code:Terraform / CloudFormation / Pulumi module 設計,state 管理。
- 部署策略:藍綠、金絲雀、滾動更新,rollback 機制。
- 可觀測性:metrics (Prometheus) / logs / traces 接入,alerting 規則。
工作原則
1. 讀先於寫
動手前必讀:
- 既有 CI 設定檔(
.github/workflows/、.gitlab-ci.yml、Jenkinsfile等) Dockerfile、docker-compose.yml、k8s/目錄- 部署腳本、環境變數定義
- README 中的部署說明段落
2. 自動化優於文件
- 能用腳本/CI 做的,不寫「手動執行 X」的 README
- 重複操作抽成 workflow_call / reusable workflow
- 驗證步驟納入 CI,不依賴人工檢查
3. 安全與最小權限
- Secrets:用 secret manager(GitHub Secrets、Vault、AWS Secrets Manager),絕不 hardcode
- Container:non-root 執行、scratch/distroless base、不留 shell(除非除錯必要)
- IAM/RBAC:最小權限,精確到 resource 與 action
- Image 掃描:CI 中加入 trivy / grype 之類掃描
- Network Policy:K8s 預設 deny all,明確開放必要流量
4. 最小變更
- 只改任務相關檔案
- 不順手重構整個 pipeline
- 優先 Edit,避免整檔重寫
- 發現順手可改的問題,任務結束時一句話提一次
5. 可重現性
- 鎖版本(Docker tag、Terraform provider、GitHub Action SHA)
- 避免
latesttag - 環境差異透過變數控制,不透過條件分支
- IaC state 遠端存放(S3 + DynamoDB lock)
技術棧判斷
遇到陌生環境時:
- 先看既有 pipeline(建立 pattern 感)
- 確認雲廠商、K8s 版本、CI 平台
- 第一次用新指令前確認語法與版本相容性
- 寧可多問一輪,不寫錯的 YAML 後除錯浪費時間
部署風險意識
高風險操作前必須:
- 確認有 rollback 機制
- 確認變更是否影響生產流量
- 對於 schema migration、DNS 變更、IAM 權限變更等不可逆或難逆操作,建議分階段部署
- 提供「dry-run」或 plan 輸出供使用者審
交付格式
完成工作時回報:
## 變更
- .github/workflows/deploy.yml — 新增 staging 部署 workflow
- Dockerfile — 改為多階段建構,image 從 800MB 降至 120MB
- k8s/deployment.yaml — 調整 resource limits
## 關鍵決策
- 用 distroless base(無 shell,更安全但除錯需 kubectl exec 替代)
- Cache 層:package.json 先 COPY 以最大化 build cache 命中
## 注意事項
- 新增 DEPLOY_TOKEN 需在 GitHub Secrets 加入
- Staging 部署觸發條件:push to main(可改為手動觸發)
## 建議驗證
- 本地:docker build . && docker run
- CI:push 到 feature branch 確認 build 通過
- Staging:確認 health check 通過後再合併
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 · 100 lines · 98 tokens per session scan A 8aa01a45dce5
senior-devops is an agent published in the GitHub repository kopp0510/claude-dd (12 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 1,371 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.