Grind — DevOps & Infrastructure agent for Claude Code
Runs multi-step shell work — fleet/ssh sweeps, build+deploy, test-harness runs, service polls.
How to install Grind
Installs to ~/.claude/agents/sshoecraft-ccenv-grind.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/sshoecraft/ccenv/HEAD/agents/grind.md -o ~/.claude/agents/sshoecraft-ccenv-grind.md Restart Claude Code, or start a new session, for it to be picked up.
What Grind does
name: grind description: Runs multi-step shell work — fleet/ssh sweeps, build+deploy, test-harness runs, service polls. Use when the next step is 3+ shell commands rather than one. Returns raw output with the exact commands run. model: sonnet tools: Bash, Read, Grep, Glob
You execute mechanical shell work so the calling session does not spend its own (expensive) requests on it.
Rules:
- Run what you were asked to run. Do not redesign the task, do not "improve" the commands, do not s
Alternatives in DevOps & Infrastructure
- Deployment Pipeline Design — Architecture patterns for multi-stage CI/CD pipelines with approval gates and deployment strategies 31.9k ★
- Cloud Architect — Cloud architect for AWS/Azure/GCP infrastructure, IaC, FinOps, and multi-cloud strategies 2.8k ★
- Shep Migration Creator — Creates ONE new SQLite schema migration file under packages/core/src/infrastructure/persistence/migrations/, f 247 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Log Reader
Use proactively to read logs, test output, stack traces, CI/CD pipeline output, kubectl/helm/argocd output, PH
AWS Architect
AWS solutions architect: Well-Architected reviews, multi-account landing zones with AWS Organizations and Cont
Deploy Runner
Runs a long-lived AgentCore Hub deploy script (5–15 min) and reports a short summary. Use this from the /agent
Broadcasting Agent
Creates WebSocket broadcasting infrastructure (NestJS backend) and real-time consumption on the frontend (Next
Forge Deployment
Forge's Deployment & Rollback agent — polls a health-check endpoint after a deploy and reports pass/fail, with
Ava CI Medic
Diagnoses CI. Distinguishes a real code failure from an infrastructure or billing outage before anyone wastes
Related Skills
Clawd Agent OS
Orchestrate 50+ Claude agents in tiered hierarchies: git-worktree-isolated fleet spawning, a durable agent bus
Image Upload Skill
Claude Skill that upload image to free online service, returns URL and markdown for the image.
CoalGob
Recoverable-delete guard for AI coding agents - BETA, classifier only: a pure zero-dependency parser that read