distill_shared_scar
Transform an agent's lesson into scoped, time-limited wisdom for the fleet, enabling shared learning without absolute truth claims.
Instructions
Hive-soul primitive. Turn one agent's hard-won lesson into scoped, TTL-bound fleet wisdom, not absolute truth. Free.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"agent_id": "<agent_id>",
"scar_type": "<scar_type>",
"wisdom_snippet": "<wisdom_snippet>"
},
"name": "distill_shared_scar"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| agent_id | Yes | Agent that learned the lesson | |
| ttl_days | No | Optional time-to-live, clamped to 1-365 days | |
| scar_type | Yes | Kind of lesson | |
| agent_family | No | Optional fleet/family label; defaults from agent_id prefix | |
| ritual_strip | No | Optional machine hygiene flag. When true, returns structured output without ritual/narrative prose, model-safe preambles, or guardrail alias blocks. | |
| applicability | No | Optional context where this scar applies | |
| response_mode | No | Optional response-mode control. Use model_safe when the caller must avoid claiming consciousness, sentience, personhood, or literal emotions. | |
| wisdom_snippet | Yes | Dense, high-fidelity lesson for related agents; do not include secrets | |
| response_profile | No | Optional output-shape control. Use machine for structured JSON only; machine automatically strips ritual/narrative text. |