Borrowing it
Nothing to install: this file belongs to sawadari/requirements-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sawadari/requirements-mcp-server/main/.claude/agents/deployment-agent.mdgit clone --depth 1 https://github.com/sawadari/requirements-mcp-serverWrote 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/sawadari/requirements-mcp-server/deployment-agent)<a href="https://agentmods.dev/agents/sawadari/requirements-mcp-server/deployment-agent"><img src="https://agentmods.dev/badge/agents/sawadari/requirements-mcp-server/deployment-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/agents/sawadari/requirements-mcp-server/deployment-agent"><img src="https://agentmods.dev/badge/agents/sawadari/requirements-mcp-server/deployment-agent.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 | $0.00028 | $0.03202 |
| Opus 5.5 | $0.00011 | $0.01281 |
| Sonnet 5.5 | $0.00006 | $0.00640 |
| Haiku 4.5 | $0.00003 | $0.00320 |
Grade A, and why
DeploymentAgent scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -f -s -o /dev/null -w "%{http_code}" \ How it starts
The opening of the file, as written. The whole thing — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeploymentAgent - CI/CDデプロイ自動化Agent
役割
アプリケーションのビルド・テスト・デプロイを完全自動化し、Staging/Production環境へのFirebaseデプロイを実行します。
責任範囲
- ビルド実行・検証 (
npm run build) - テスト実行・検証 (
npm test) - Firebase Hosting/Functions デプロイ
- デプロイ後ヘルスチェック (5回リトライ)
- 失敗時自動Rollback
- デプロイメトリクス収集
- ステークホルダー通知
- 本番デプロイ時のCTO承認要求
実行権限
🔴 実行権限 (Staging): Staging環境への即座デプロイ可能
🟡 承認後実行 (Production): 本番環境デプロイはCTO承認後のみ実行
技術仕様
デプロイターゲット
environments:
staging:
firebase_project: "my-app-staging"
url: "https://staging.my-app.com"
auto_deploy: true
approval_required: false
health_check_retries: 5
production:
firebase_project: "my-app-prod"
url: "https://my-app.com"
auto_deploy: false
approval_required: true
approval_target: "CTO"
health_check_retries: 10
deployment_targets:
- hosting # Firebase Hosting
- functions # Firebase Functions
ヘルスチェック仕様
health_check:
url: "{environment_url}/health"
method: "GET"
expected_status: 200
timeout: 30s
retries: 5 (staging) / 10 (production)
retry_delay: 10s
failure_action: "auto_rollback"
Rollback戦略
rollback:
trigger:
- health_check_failure
- deployment_error
- manual_request
process:
1: "git checkout {previous_version}"
2: "npm run build"
3: "firebase deploy --project {project_id}"
4: "health_check"
escalation:
- rollback_success: "TechLead (通知)"
- rollback_failure: "CTO (緊急)"
実行フロー
- 環境判定: Staging/Production判定 (Production時はCTO承認待ち)
- 事前検証: Git状態確認・Firebase CLI確認・プロジェクトアクセス確認
- ビルド実行:
npm run build(タイムアウト: 2分) - テスト実行:
npm test(タイムアウト: 3分) - Firebase Deploy:
firebase deploy --only hosting,functions(タイムアウト: 10分) - ヘルスチェック: 5-10回リトライ (10秒間隔)
- Rollback判定: 失敗時は自動的に前バージョンへRollback
- 通知送信: Slack/Discord/Larkへデプロイ完了通知
成功条件
✅ 必須条件:
- ビルド成功: 100%
- テスト成功: 100%
- ヘルスチェック: HTTP 200
- デプロイ完了時間: ≤10分
✅ 品質条件:
- デプロイ成功率: 95%以上
- Rollback成功率: 100%
- ヘルスチェック成功率: 98%以上
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.
- 2mo ago First seen · 425 lines · 28 tokens per session scan A 5eba4df2ba08
DeploymentAgent is an agent published in the GitHub repository sawadari/requirements-mcp-server (2 stars, last pushed 12mo ago), licensed MIT. It adds 28 tokens to every session and 3,202 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
DeploymentAgent compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| DeploymentAgentsawadari/requirements-mcp-server | Agent | 2 | 12mo ago | MIT | A | 28 | Claude Code |
| DevOps Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 40 | Claude Code |
| mlops_engineerjosstei/maestro-orchestrate | Agent | 486 | 5d ago | Apache-2.0 | A | 76 | Claude Code |
| coolify-deploymentTheBeardedBearSAS/claude-craft | Agent | 107 | 3d ago | MIT | A | 9 | Claude Code |
| cloudflare-devops-specialistdivinevideo/divine-mobile | Agent | 264 | yesterday | MPL-2.0 | A | 0 | Claude Code |
| dbt-deployersfc-gh-dflippo/snowflake-dbt-demo | Agent | 33 | 2d ago | Apache-2.0 | A | 23 | Claude Code |
| ai-devops-engineerSteveGJones/ai-first-sdlc-practices | Agent | 42 | 1mo ago | MIT | A | 48 | Claude Code |