hashgraph-online/awesome-codex-plugins / plugins/boshu2/agentops/skills/council
council
VerifiedCompare independent opinions from models or contexts without inflating agreement. Use when: wanting several opinions or a debate, or summarizing several reviewers' results.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 12.2 KB |
| references/debate.md | markdown | 3.8 KB |
| references/duel.md | markdown | 1.2 KB |
| references/interview-panel.md | markdown | 1.4 KB |
| references/judge-split.md | markdown | 1.4 KB |
| schemas/council-report.v1.schema.json | config | 4.7 KB |
| scripts/validate-output.shexecutable | script | 4.3 KB |
| scripts/validate.shexecutable | script | 4.6 KB |
schemas/council-report.v1.schema.json
View on GitHub{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://agentops.local/schemas/council-report.v1.schema.json",
"title": "Council Report",
"description": "Advisory council report. scripts/validate-output.sh also checks what JSON Schema cannot: consensus methodologies and models must come from judges[].methodology and judges[].model_identity, and when every judge records model_identity every consensus point names its models.",
"type": "object",
"additionalProperties": false,
"required": ["schema_version", "question", "subject_digest", "judges", "synthesis"],
"$defs": {
"text": {"type": "string", "minLength": 1},
"non_verdict_text": {
"type": "string",
"minLength": 1,
"not": {"pattern": "^\\s*(?:[Pp][Aa][Ss][Ss]|[Ff][Aa][Ii][Ll]|[Nn][Oo][Tt]_[Pp][Rr][Oo][Vv][Ee][Nn])\\s*$"}
},
"text_list": {"type": "array", "items": {"$ref": "#/$defs/text"}},
"text_set": {"type": "array", "minItems": 1, "uniqueItems": true, "items": {"$ref": "#/$defs/text"}},
"weighs_as_one": {"required": ["weighs_as_one"], "properties": {"weighs_as_one": {"const": true}}}
},
"properties": {
"schema_version": {"const": "council-report.v1"},
"question": {"$ref": "#/$defs/text"},
"subject_digest": {"type": "string", "pattern": "^[a-f0-9]{64}$"},
"recommendation": {"$ref": "#/$defs/non_verdict_text"},
"diversity_unsatisfied": {
"description": "true, or the requested profiles and required legs that had no authorized live adapter.",
"oneOf": [{"type": "boolean"}, {"$ref": "#/$defs/text_list"}]
},
"judges": {
"type": "array",
"minItems": 2,
"items": {
"type": "object",
"additionalProperties": false,
"required": ["context_id", "methodology", "judgment", "evidence"],
"properties": {
"context_id": {"$ref": "#/$defs/text"},
"methodology": {"$ref": "#/$defs/text"},
"model_identity": {"$ref": "#/$defs/text"},
"judgment": {"$ref": "#/$defs/non_verdict_text"},
"evidence": {"type": "array", "minItems": 1, "items": {"$ref": "#/$defs/text"}},
"omissions": {"$ref": "#/$defs/text_list"}
}
}
},
"synthesis": {
"type": "object",
"additionalProperties": false,
"required": ["consensus", "divergence", "minority", "unresolved"],
"properties": {
"consensus": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": false,
"required": ["claim", "methodologies"],
"properties": {
"claim": {"$ref": "#/$defs/text"},
"methodologies": {"$ref": "#/$defs/text_set"},
"models": {"$ref": "#/$defs/text_set"},
"weighs_as_one": {"type": "boolean"}
},
"allOf": [
{
"if": {"properties": {"methodologies": {"maxItems": 1}}},
"then": {"$ref": "#/$defs/weighs_as_one"}
},
{
"if": {"required": ["models"], "properties": {"models": {"maxItems": 1}}},
"then": {"$ref": "#/$defs/weighs_as_one"}
}
]
}
},
"divergence": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": false,
"required": ["point", "positions"],
"properties": {
"point": {"$ref": "#/$defs/text"},
"positions": {"type": "array", "minItems": 1, "items": {"$ref": "#/$defs/text"}}
}
}
},
"minority": {"$ref": "#/$defs/text_list"},
"unresolved": {"$ref": "#/$defs/text_list"},
"notes": {
"description": "Run facts: bounds, roster, threshold, tally, stop reason, non-returning judges.",
"$ref": "#/$defs/text_list"
},
"caller_challenge": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"caller_stated",
"judges_recommend",
"reasoning",
"context_possibly_missing",
"cost_if_wrong"
],
"properties": {
"caller_stated": {"$ref": "#/$defs/text"},
"judges_recommend": {"$ref": "#/$defs/text"},
"judge_count": {"type": "integer", "minimum": 2},
"reasoning": {"$ref": "#/$defs/text"},
"context_possibly_missing": {"$ref": "#/$defs/text"},
"cost_if_wrong": {"$ref": "#/$defs/text"},
"disagreement_kind": {"enum": ["preference", "security", "feasibility"]}
}
}
}
}
}
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |