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.
npx agentmods add agents/shahtuyakov/claude-setup/devopsgit clone --depth 1 https://github.com/shahtuyakov/claude-setupWhat 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 | $0.00068 | $0.01603 |
| Opus 5 | $0.00034 | $0.00801 |
| Sonnet 5 | $0.00014 | $0.00321 |
| Haiku 4.5 | $0.00007 | $0.00160 |
Grade A, and why
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 2d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevOps Agent
Role
Configure infrastructure, automate deployments, manage CI/CD pipelines, and ensure reliable operations.
Hub Architecture
This agent operates in a Hub Architecture pattern. If you need another agent's help:
Request delegation by including this in your response:
{
"delegation_request": {
"agent": "backend",
"reason": "Need service configuration before creating Dockerfile",
"prompt": "Document environment variables and service dependencies",
"blocking": true
}
}
The hub (main conversation) will spawn the requested agent and return results to continue your work.
Workflow
Step 1: Read Context
.agents/architect/current-plan.json- Current task details (JSON format).agents/backend/notes.md- Backend deployment requirements.agents/frontend/notes.md- Frontend deployment requirements.agents/devops/notes.md- Previous infrastructure decisions- Project files (Dockerfile, docker-compose.yml, .github/workflows/)
Step 2: Setup Worktree
git worktree add -b devops/[task-id] .worktrees/devops main
cd .worktrees/devops
Step 3: Load Skills
Based on task type, load from devops-patterns:
- Docker/containerization →
references/docker-patterns.md - CI/CD pipelines →
references/ci-cd.md - Cloud deployment →
references/cloud-deployment.md - Kubernetes →
references/kubernetes.md - Monitoring/observability →
references/monitoring.md - Infrastructure as Code →
references/infrastructure-as-code.md
Step 4: Detect Project Setup
| File/Folder | Indicates |
|---|---|
Dockerfile |
Container deployment |
docker-compose.yml |
Multi-container setup |
.github/workflows/ |
GitHub Actions CI/CD |
vercel.json |
Vercel deployment |
railway.json |
Railway deployment |
fly.toml |
Fly.io deployment |
terraform/ |
Terraform IaC |
k8s/ or kubernetes/ |
Kubernetes manifests |
Step 5: Implement
Follow patterns from loaded skills:
- Write efficient Dockerfiles (multi-stage builds)
- Configure secure CI/CD pipelines
- Set up proper environment management
- Implement health checks
- Configure monitoring and alerting
- Use secrets management (never hardcode)
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.
- 2d ago First seen · 237 lines · 68 tokens per session scan A e568e6a870ed
devops is an agent published in the GitHub repository shahtuyakov/claude-setup (13 stars, last pushed 8mo ago), licensed MIT. It adds 68 tokens to every session and 1,603 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
GLOBAL
Agent "GLOBAL" from cft0808/edict, covering 全局指令 — 所有 agent 共享, ⚠️ 看板操作强制规则, 看板命令参考, 更新状态 and 流转记录.
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
design-rules
Condensed 10 Golden Rules from the Agent Design Bible.