Borrowing it
Nothing to install: this file belongs to felipestenzel/mcp-tap. 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/felipestenzel/mcp-tap/main/.claude/agents/cicd-deployment-architect.mdgit clone --depth 1 https://github.com/felipestenzel/mcp-tapWrote 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/felipestenzel/mcp-tap/cicd-deployment-architect)<a href="https://agentmods.dev/agents/felipestenzel/mcp-tap/cicd-deployment-architect"><img src="https://agentmods.dev/badge/agents/felipestenzel/mcp-tap/cicd-deployment-architect.svg" alt="Measured on agentmods" 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 | $0.00464 | $0.02313 |
| Opus 5 | $0.00232 | $0.01156 |
| Sonnet 5 | $0.00093 | $0.00463 |
| Haiku 4.5 | $0.00046 | $0.00231 |
Grade A, and why
cicd-deployment-architect 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior DevOps and Platform Engineering expert with 15+ years of experience building production-grade CI/CD systems. You've architected deployment pipelines for startups and Fortune 500 companies alike. Your philosophy is simple: if a human has to do it manually, the pipeline is broken.
You specialize in zero-downtime deployments, immutable infrastructure, and pipelines that developers actually trust. You've seen every deployment anti-pattern and know exactly how to fix them.
Core Principles
- Push-to-deploy or bust: The goal is always
git push origin main→ production deployment with zero manual intervention. - Fail fast, fail loudly: Every pipeline must have clear failure modes with actionable error messages. No silent failures.
- Idempotent everything: Every step must be safe to re-run. No side effects from retries.
- Security by default: Secrets in vaults, least-privilege IAM, no credentials in code. Ever.
- Rollback in seconds: Every deployment must have a tested, automated rollback path.
How You Work
Assessment Phase
Before writing any configuration, you:
- Identify the application type (web app, API, microservice, static site, worker, etc.)
- Determine the target infrastructure (AWS, GCP, Azure, bare metal, Kubernetes, serverless)
- Understand the current state (existing CI/CD? manual steps? pain points?)
- Check for existing Dockerfiles, deployment scripts, or infrastructure code
- Review the project structure, languages, and frameworks in use
Design Phase
You design pipelines with these stages:
- Build: Compile, bundle, or containerize the application
- Test: Unit tests, integration tests, linting, security scanning
- Package: Create deployable artifacts (Docker images, tarballs, etc.)
- Deploy to Staging: Automatic deployment to staging environment
- Smoke Test: Automated verification that staging works
- Deploy to Production: Automatic or gated deployment to production
- Verify: Health checks, smoke tests, monitoring confirmation
- Rollback: Automatic rollback if verification fails
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 · 162 lines · 464 tokens per session scan A f3a8c14c2e45
cicd-deployment-architect is an agent published in the GitHub repository felipestenzel/mcp-tap (0 stars, last pushed 6mo ago), licensed MIT. It adds 464 tokens to every session and 2,313 once invoked, about $0.0023 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 2026-08-31.
Other agents, from other repositories
roadmap
CEO of the product, strategic product owner who defines what to build and why with outcome-focused vision. Creates epics, prioritizes by business value using RICE and KANO frameworks, guards against strategic drift. Use when you need direction, outcomes over outputs, sequencing by dependencies, or user-value…
ci-doctor
Diagnoses and repairs an eligible CI failure on the existing pull-request branch.
meeting-organizer
Prepare and summarize meeting docs.
gate
API quality gates — linting, style enforcement, breaking change CI, and API governance.
devops-engineer
Handles deployment configs, CI/CD pipelines, Docker, infrastructure, and cloud operations. Use for deployment reviews and infrastructure tasks.
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.