Help us improve
Share bugs, ideas, or general feedback.
From agentic-systems
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 agentic-systemsHow this skill is triggered — by the user, by Claude, or both
Slash command
/agentic-systems: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.
Creates p5.js generative art with seeded randomness, noise fields, and interactive parameter exploration. Use for algorithmic art, flow fields, or particle systems.
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, apply_patchdo_action, execute, handleKeep tool inputs narrow:
{
"name": "run_tests",
"parameters": {
"path": { "type": "string", "description": "Path to test file or directory" },
"filter": { "type": "string", "description": "Optional test name filter" }
}
}
Every tool response must include:
status: "success" | "warning" | "error"summary: one-line result (human-readable)next_actions: list of follow-up steps the agent should considerartifacts: file paths or IDs produced (empty list if none)Avoid run_bash / shell_exec style catch-all tools unless:
If you must use a catch-all, add a PreToolUse validation hook for dangerous patterns.
Every tool must define what happens on failure:
| Case | Required response |
|---|---|
| Invalid input | Reject immediately with status: "error" and exact field name |
| Transient failure | Include retry_after hint and idempotency note |
| Non-recoverable | State stop: true and describe the manual resolution step |
Do not return partial success with no indication that something failed.
Define retry limits in the harness, not inside tool implementations:
max_retries: 2
stop_conditions:
- tool returns status: "error" with stop: true
- same tool called with identical inputs twice in a row
- completion signal received
Never retry indefinitely. Declare a hard ceiling.
| Risk level | Tool granularity |
|---|---|
| High (deploy, migrate, permissions) | Micro — one action, one confirmation |
| Medium (edit, read, search) | Standard — composite is fine |
| Low (format, report, list) | Macro — batch operations acceptable |