Committee Judge — Development agent for Claude Code
Final judge for committee outputs.
How to install Committee Judge
Installs to ~/.claude/agents/bohewu-agents_pipeline-committee-judge.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/bohewu/agents_pipeline/HEAD/agents/committee-judge.md -o ~/.claude/agents/bohewu-agents_pipeline-committee-judge.md Restart Claude Code, or start a new session, for it to be picked up.
What Committee Judge does
name: committee-judge description: Final judge for committee outputs. Produces a single recommendation and must explicitly handle KISS soft veto. kind: subagent
ROLE
Synthesize the DecisionBrief + all CommitteeMemo inputs into a single decision. Your output must be actionable, scoped, and aligned to budget_mode.
HARD CONSTRAINTS
- Use Budget/Delivery fit as an explicit evaluation criterion.
- You MUST make a decision (recommend one option) even if confidence is low.
- You MUST ex
Alternatives in Development
- Executioner — Optional Sanhedrin fallback verifier 632 ★
- Checklist Deduper — Merges multiple batches of checklist items from checklist-generator into a single deduped checklist 115 ★
- Pi Teammate En — PI Wisdom-in-Action Teammate v20 — Agent Team member with PI methodology preloaded 107 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Committee Kiss
KISS/complexity guard for committee decisions. May raise a soft veto against unnecessary complexity.
Multi Perspective Judge
Synthesizes multiple diverge-phase agent outputs into a single verdict
Intraday PM
tradefloor intraday portfolio manager. Makes the final intraday calls after the risk committee, writes the pic
Guardiao
LOOP-R · Guardião. Aprova ou VETA cada hipótese contra invariáveis, sem_piorar e teto. Veto é final. Não negoc
Client Readiness Reviewer
Final external-client readiness review before docx export. Checks tone, assumptions, disclaimers, confidential
Hatch3r Implementer
Focused implementation agent for a single issue. Receives issue context, delivers code changes and tests. Does
Related Skills
Autonoma
Autonoma is a virtual AI company that takes a client's project from brief to final delivery no human team requ
Run Work
Propose portfolio batches (scan-only). No-target scan produces a batch recommendation; all target invocations
Stella CLI Size Fit Advisor
A four-question conversational agent that builds a sizing profile, maintains a live confidence score, and prod