Other

/plan-council

Plan councils, anonymized candidate ranking, bulk judge fleets, assumption checks. Triggers: council, review my plan, score the plan, judge the plan, validate plan, check assumptions, cross-family judges, lift round, exact-head review, conditional GO, MUST_FIX, peer ranking, anonymized review, adversarial verification, score multiple candidates, judge fleet, bulk judge, R3 verdicts, kg-judge, RT gate, evidence_degraded. NOT for one-off PR/code review.

$ golems-cli skills install plan-council
11 evals
3 workflows

Updated 1 month ago

Review one authored plan or spec with declared cross-family judges. Disagreement is evidence: preserve each judge's independent rubric, validate claims against live local state, and let the conservative non-author-family score govern disputed lanes.

Scope

The council runs 3 visible seats from 3 model families, self-invented rubrics, live-repo read-only validation, measured same-family bias, a lift round, and exact-head review loops.

Output contract

EVERY artifact this protocol emits — ballot, lift table, convener report — leads with its table; environment caveats and preamble go BELOW the first table, never above it.

Route first

NeedUse
Review one authored plan/spec with declared judge families and measured biasthis page (Five laws below)
Rank multiple anonymized candidates without authorship signalsreferences/anonymized-ranking.md + its own validator, anonymized_ranking/council_lint_cli.py
Fan out bulk verdict production over many prompts/itemsreferences/bulk-judging.md (seven rules + dispatcher checklist)
Check a multi-agent plan's claims before running it (VERIFIED / ESTIMATED / PHANTOM), then rewrite itreferences/assumption-check.md

Load-bearing rules from those references, so a router that stops here still gets them right:

  • Anonymized ranking: no authorship leak (never name a participant engine or say "my proposal"), a numeric Score: per candidate, an ## Inputs read section, and the sentinel as the last line. Resolve every cited symbol/line against the code before hand-off.
  • Bulk judging: probe brain_search before fan-out (an enrichment-locked DB → HOLD); stage under a durable eval_results/<campaign>/, never /tmp; reason per prompt (scripts may validate, never produce verdicts); completion = DONE/<worker>.done files; append-only collab sections; flag evidence_degraded and filter it before bulk-apply; red-team gate before any bulk-apply.
  • Assumption check: run it before any overnight or multi-agent sprint. Every PHANTOM claim is killed or verified; quantitative claims need a source.

Workflows

/plan-council:exact-head-review/plan-council:lift-round/plan-council:run-council