Stats
Actions
Tags
From dev-vitals
Design agent tool sets with stable names, narrow schemas, deterministic output shapes, and explicit error paths. No catch-all tools unless unavoidable.
How this skill is triggered — by the user, by Claude, or both
Slash command
/dev-vitals:agent-harness-designThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use when designing or improving how an agent invokes tools, handles errors, and decides when to stop.
Use when designing or improving how an agent invokes tools, handles errors, and decides when to stop.
read_file, run_tests); no generic names (do_action, execute)status (success/warning/error), summary, next_actions, artifactsrun_bash/shell_exec unless task is genuinely open-ended; add allowlist| Case | Required response |
|---|---|
| Invalid input | Reject immediately with exact field name |
| Transient failure | Include retry_after hint and idempotency note |
| Non-recoverable | Set stop: true, describe manual resolution |
Define in harness, not inside tools:
status: "error" with stop: true; same inputs called twice in a row| Risk | Granularity |
|---|---|
| High (deploy, migrate, permissions) | Micro — one action, explicit confirmation |
| Medium (edit, read, search) | Standard composite |
| Low (format, list, report) | Macro batch acceptable |
npx claudepluginhub yeaight7/agent-powerups --plugin dev-vitalsGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.