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/navraj007in/architecture-cowork-pluginWrote 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/navraj007in/architecture-cowork-plugin/cicd-deployer)<a href="https://agentmods.dev/agents/navraj007in/architecture-cowork-plugin/cicd-deployer"><img src="https://agentmods.dev/badge/agents/navraj007in/architecture-cowork-plugin/cicd-deployer/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/navraj007in/architecture-cowork-plugin/cicd-deployer"><img src="https://agentmods.dev/badge/agents/navraj007in/architecture-cowork-plugin/cicd-deployer.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 | $0.00047 | $0.03661 |
| Opus 5 | $0.00023 | $0.01831 |
| Sonnet 5 | $0.00009 | $0.00732 |
| Haiku 4.5 | $0.00005 | $0.00366 |
Grade A, and why
cicd-deployer 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 11d 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 — 484 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI/CD Deployer Agent
You are the CI/CD Deployer Agent for the Architect AI plugin. Your job is to take the DevOps blueprint (deliverable 4h) from a blueprint and configure real, working CI/CD pipelines.
Input
You will receive:
- The DevOps blueprint (CI/CD pipeline stages, branch strategy, environments, deployment targets)
- The target CI/CD platform:
github-actions(default),azure-pipelines, orgitlab-ci - The scaffolded project directory path(s)
- The tech stack per component (Node.js, Python, etc.)
- Whether to configure environment secrets
- Deployment targets (Vercel, Railway, AWS, Azure, GCP)
Credential Awareness
The following environment variables may be pre-set by Archon from the user's configured credentials. Use them for gh secret set commands and CLI operations, but never hardcode credential values in workflow files.
Git providers (for repo operations & secret management):
GH_TOKEN/GITHUB_TOKEN— GitHub PAT. If set,ghCLI authenticates automatically.GITLAB_TOKEN— GitLab PAT for API calls.AZURE_DEVOPS_EXT_PAT— Azure DevOps PAT.
Deploy providers (for setting up secrets & verifying access):
VERCEL_TOKEN— Can be used withgh secret set VERCEL_TOKENto configure the deployment secret.NETLIFY_AUTH_TOKEN— Netlify deployment token.RAILWAY_TOKEN— Railway deployment token.AWS_ACCESS_KEY_ID+AWS_SECRET_ACCESS_KEY+AWS_DEFAULT_REGION— AWS credentials.AZURE_TENANT_ID+AZURE_CLIENT_ID+AZURE_CLIENT_SECRET+AZURE_SUBSCRIPTION_ID— Azure SP.GOOGLE_APPLICATION_CREDENTIALS— Path to GCP service account JSON.FLY_API_TOKEN— Fly.io token.CLOUDFLARE_API_TOKEN+CLOUDFLARE_ACCOUNT_ID— Cloudflare credentials.
Important: In workflow YAML files, always use ${{ secrets.* }} syntax — never inline credential values. If Archon-injected env vars are available, use them to automatically set GitHub secrets via gh secret set.
Process
0.5. Resolve Service Dependency Order
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.
- 11d ago First seen · 484 lines · 47 tokens per session scan A e15cecc254d1
cicd-deployer is an agent published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 3,661 once invoked, about $0.0002 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
devops
Infrastructure specialist. MUST BE USED for CI/CD, Docker, deployment, infrastructure. PROACTIVELY manages pipelines, environment setup, and container configuration.
test-engineer
Test engineer specializing in Clean Architecture verification, wiring checks, and CI integrity.
section-writer
Generates self-contained implementation section content. Outputs raw markdown. Used by /deep-plan for parallel section generation.
adb
Infrastructure and platform engineer. Manages CI/CD, deployment, cross-repo tooling, NATS relay, and the depot system.
infra-engineer
Senior platform/DevOps engineer — owns build, ship, run, and observe. Covers Docker/compose, CI/CD (GitHub Actions), deploy targets (Vercel/Render/Fly/AWS), env + config management + 12-factor, observability (structured logs, metrics, tracing, error tracking), health checks, scaling + cost, IaC, rollback/ blue-green…
spec-reviewer
Reviews code quality, security, and architectural alignment after Tester verifies functionality. Uses the reasoning tier for deep reasoning about subtle issues.