Ops Deploy

What it does

When your agent uses it

• Tasks that involve Deployment
• Tasks that involve CI/CD

Example prompts

• “/ops-deploy”

Requirements

• A credential in VERCEL_TOKEN
• Pre-approved tools (allowed-tools): Bash, Read, Grep, Glob, Skill, Agent, TeamCreate, SendMessage, AskUserQuestion, TaskCreate, TaskUpdate, Monitor, WebFetch, mcp__claude_ai_Vercel__list_deployments, mcp__claude_ai_Vercel__list_projects, mcp__claude_ai_Vercel__get_deployment, mcp__claude_ai_Vercel__get_runtime_logs, mcp__claude_ai_Vercel__get_deployment_build_logs

Workflow steps

2 steps, taken from the step headings in SKILL.md.

1. 1Gather deploy data in parallel
2. 2Render dashboard

What it can do on your machine

Read from SKILL.md and the folder at commit 10bfc43. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • Read
  • Grep
  • Glob
  • Skill
  • Agent
  • TeamCreate
  • SendMessage
  • AskUserQuestion
  • TaskCreate

  …and 8 more on the same allowed-tools line.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • aws
  • jq
  • gh
  • vercel

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • api.vercel.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • VERCEL_TOKEN
  • AWS_ACCESS_KEY_ID

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ops Deploy loads about 1.9k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 436 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~38

When it runs · the whole SKILL.md, loaded when a task matches

~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, Read, Grep, Glob, Skill, Agent, TeamCreate, SendMessage, AskUserQuestion, TaskCreate, TaskUpda

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from davepoon/buildwithclaude at commit 10bfc43, republished under its MIT licence (© davepoon). 436 words, ~1,884 tokens.

name

ops-deploy

description

Deploy status across all projects. Shows ECS service versions, Vercel deployments, recent deploys, pending deploys, and CI/CD pipeline state.

allowed-tools

Bash, Read, Grep, Glob, Skill, Agent, TeamCreate, SendMessage, AskUserQuestion, TaskCreate, TaskUpdate, Monitor, WebFetch, mcp__claude_ai_Vercel__list_deployments, mcp__claude_ai_Vercel__list_projects, mcp__claude_ai_Vercel__get_deployment, mcp__claude_ai_Vercel__get_runtime_logs, mcp__claude_ai_Vercel__get_deployment_build_logs

argument-hint

[project-alias|ecs|vercel|all]

effort

low

maxTurns

20

disallowedTools

Edit, Write, NotebookEdit

TeamCreate("deploy-team")
Agent(team_name="deploy-team", name="ecs-checker", prompt="List all ECS clusters and describe service health, running/desired counts")
Agent(team_name="deploy-team", name="vercel-checker", prompt="List Vercel projects and recent deployments with status")
Agent(team_name="deploy-team", name="ci-checker", prompt="Check GitHub Actions runs across all registered repos for failures")

${CLAUDE_PLUGIN_ROOT}/bin/ops-infra 2>/dev/null || \
aws ecs list-clusters --output json 2>/dev/null

for cluster in $(aws ecs list-clusters --output json 2>/dev/null | jq -r '.clusterArns[]'); do
  cluster_name=$(basename "$cluster")
  aws ecs list-services --cluster "$cluster_name" --output json 2>/dev/null | \
    jq -r '.serviceArns[]' | while read svc; do
    aws ecs describe-services --cluster "$cluster_name" --services "$svc" \
      --output json 2>/dev/null | jq '.services[] | {name: .serviceName, desired: .desiredCount, running: .runningCount, pending: .pendingCount, image: (.taskDefinition // "unknown"), status: .status}'
  done
done

REGISTRY="${CLAUDE_PLUGIN_ROOT}/scripts/registry.json"
[ -f "$REGISTRY" ] || REGISTRY="${CLAUDE_PLUGIN_ROOT}/scripts/registry.example.json"
for repo in $(jq -r '.projects[] | select(.gsd == true) | .repos[]' "$REGISTRY" 2>/dev/null); do
  echo "=== $repo ==="
  gh run list --repo "$repo" --limit 5 --json status,conclusion,name,headBranch,createdAt,databaseId 2>/dev/null
done

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 OPS ► DEPLOY STATUS — [timestamp]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

ECS SERVICES
 CLUSTER    SERVICE         D/R/P   STATUS   LAST DEPLOY
 ─────────────────────────────────────────────────────
 [cluster]  [service]       [x/x/x] ACTIVE   [time ago]
 ...

VERCEL DEPLOYMENTS
 PROJECT     ENV        STATUS    COMMIT    DEPLOYED
 ─────────────────────────────────────────────────────
 [project]   production  READY    [sha]     [time ago]
 ...

CI/CD PIPELINE
 REPO              BRANCH   WORKFLOW        STATUS    AGE
 ─────────────────────────────────────────────────────
 example-api       main     Deploy API      ✓ success  2h
 example-web       dev      Build            ✗ failure  1h
 ...

PENDING DEPLOYS (branch ready, not yet deployed)
 [repo] [branch] [PR#] [CI status] → needs merge to trigger

──────────────────────────────────────────────────────

  [View logs for [failing service]]
  [Trigger manual deploy for [project]]
  [View build logs for [failing CI run]]
  [More actions...]

  [Check Vercel [project] runtime logs]
  [Open GitHub Actions for [repo]]
  [Back to dashboard]

Trigger deploy for [project]:
  Environment: [production/staging]
  Branch: [branch]
  Last commit: [sha] — [message]

  [Deploy now]  [View diff since last deploy first]  [Cancel]

  [Dispatch fix agent for this failure]  [Redeploy]  [Back to dashboard]

Monitor(command: "gh run watch <run-id> --repo <repo>")

WebFetch(url: "https://api.vercel.com/v6/deployments?projectId=<id>&limit=5", headers: {"Authorization": "Bearer $VERCEL_TOKEN"})

© davepoon, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/claude-ops/skills/ops-deploy of davepoon/buildwithclaude.

Open the folder on GitHubat commit 10bfc43