Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
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.
npx claudepluginhub yeaight7/agent-powerups --plugin dev-vitalsHow 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.
Guides technical evaluation of code review feedback: read fully, restate for understanding, verify against codebase, respond with reasoning or pushback before implementing.
Share bugs, ideas, or general feedback.
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 |