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/commands/navraj007in/architecture-cowork-plugin/setup-cicd)<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/setup-cicd"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/setup-cicd/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/commands/navraj007in/architecture-cowork-plugin/setup-cicd"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/setup-cicd.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 | $0.00021 | $0.01517 |
| Opus 5.5 | $0.00008 | $0.00607 |
| Sonnet 5.5 | $0.00004 | $0.00303 |
| Haiku 4.5 | $0.00002 | $0.00152 |
Grade A, and why
setup-cicd 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architect:setup-cicd
Trigger
/architect:setup-cicd
Purpose
After generating a blueprint with /architect:blueprint, this command takes the DevOps blueprint (deliverable 4h) and configures real, working CI/CD pipelines. Creates workflow files, sets up deployment stages, and lists required secrets. Supports GitHub Actions (default), Azure Pipelines, and GitLab CI.
Workflow
Step 1: Read Context
First, check for architecture-output/_state.json. If it exists, read it in full and extract:
project.name→ product name for workflow file commentstech_stack.deployment→ default deployment target (Vercel, Railway, AWS, etc.) — pre-fill Step 2 questiontech_stack.frontend,tech_stack.backend→ framework detection for build commands (e.g. Next.js →npm run build, Go →go build ./...)components→ list of components to configure pipelines for
Then, read the SDL and extract architecture.services[].dependsOn[] to determine service dependency order. Services with no dependents should build/deploy first. Services that depend on others should deploy after their dependencies are healthy. Include this ordering in the CI/CD pipeline job dependencies (needs: in GitHub Actions). Check solution.sdl.yaml first; if absent, read sdl/README.md then the relevant module (typically sdl/architecture.yaml or sdl/services.yaml).
Then, check if a blueprint with a DevOps section (deliverable 4h) exists earlier in the conversation.
If no DevOps blueprint exists, respond:
"I need a DevOps blueprint to configure from. Run
/architect:blueprintfirst to generate your CI/CD pipeline design, then come back here to set it up."
Step 2: Ask Configuration
Ask the user:
"Which CI/CD platform?"
- GitHub Actions (default) — Most common for GitHub repos
- Azure Pipelines — For Azure DevOps projects
- GitLab CI — For GitLab repos
"Which project(s) should I configure?" (path or all scaffolded projects)
"Where are you deploying?"
- Vercel, Railway, AWS, Azure, GCP, Docker/self-hosted
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 · 156 lines · 21 tokens per session scan A 865871144aff
setup-cicd is a command published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 1,517 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
nyann:wait-for-pr-checks
Poll a GitHub PR's checks until they all pass, any one fails, or a timeout is hit. Returns a structured outcome the caller can gate on.
nyann:watch
Start (or stop) a CI sentinel for the current repo's open PRs — a one-shot foreground poll by default, or a supervised background daemon with --daemon. Also manage a multi-repo watch-list and poll every watched repo at once. Notifications surface in your next session via the session-start hook.
nyann:gen-ci
Generate a GitHub Actions CI workflow (.github/workflows/ci.yml) from the project's nyann profile and detected stack. Produces lint, typecheck, and test jobs matching the hook configuration.
ccc-makeover
Score project health with X-Ray, apply the top recommendations in impact order with your OK for each, and show the before and after score. Use when you want the highest-impact project health fixes applied and measured.
do
Universal command that intelligently routes to appropriate craft commands.
sm-buff
You usually don't run buff directly — run sm sail. sm sail drives the whole PR to green and calls buff watch / triage for you, stopping only when it needs you to act (see /sm-sail). Reach for sm buff here only for surgical work: inspecting a specific failure, or resolving a single review thread when sail has parked on…