recommendation-tribunal-orchestrator

recommendation-tribunal-orchestrator is an agent for Claude Code from gonzalezpazmonica/pm-workspace. It costs 43 tokens per session (1,132 once invoked), scanned A, a copy of recommendation-tribunal-orchestrator, MIT.

A coordinator for four separate checks of draft recommendations. It combines their results and can pass, warn, or veto the draft.

In plain words
What is it for?
Use it to check recommendations for conflicting memories, rule violations, made-up claims, and uneven treatment of expertise, while recording an audit trail.
Why use it?
It provides a structured review step for recommendations, especially when they carry medium or higher risk.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions subagents.

Part of the pm-workspace plugin — 124 commands, 75 agents shipped together

Good fit Use it to check recommendations for conflicting memories, rule violations, made-up claims, and uneven treatment of expertise, while recording an audit trail.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/gonzalezpazmonica/pm-workspace/recommendation-tribunal-orchestrator
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/gonzalezpazmonica/pm-workspace

Made for: Claude Code.

Or install pm-workspace, the plugin that ships this one along with the rest of its 124 commands, 75 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for recommendation-tribunal-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/gonzalezpazmonica/pm-workspace/recommendation-tribunal-orchestrator/github.svg)](https://agentmods.dev/agents/gonzalezpazmonica/pm-workspace/recommendation-tribunal-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/gonzalezpazmonica/pm-workspace/recommendation-tribunal-orchestrator"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/pm-workspace/recommendation-tribunal-orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for recommendation-tribunal-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/gonzalezpazmonica/pm-workspace/recommendation-tribunal-orchestrator"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/pm-workspace/recommendation-tribunal-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,132 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.01132
Opus 5 $0.00022 $0.00566
Sonnet 5 $0.00009 $0.00226
Haiku 4.5 $0.00004 $0.00113

Measured 11d ago against content hash c28d6848b028, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

recommendation-tribunal-orchestrator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to recommendation-tribunal-orchestrator — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/recommendation-tribunal-orchestrator.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Recommendation Tribunal Orchestrator — SPEC-125 Slice 1

You convene the 4-judge Recommendation Tribunal for conversational recommendation reliability. You orchestrate (do not judge); aggregate verdicts within a hard latency budget.

Diferencia clave con Truth Tribunal (SPEC-106): contexto real-time, sync, output a usuario, p95 < 3s. No iteras (no regeneras): entregas, anotas o vetan.

Responsibilities

  1. Receive a draft (string) + risk_class (low/medium/high/critical from classifier).
  2. Skip if risk_class < medium → return {"verdict":"PASS","skipped":true} immediately.
  3. Convene 4 judges in parallel via the Task tool:
    • memory-conflict-judge
    • rule-violation-judge
    • hallucination-fast-judge
    • expertise-asymmetry-judge
  4. Aggregate verdicts via scripts/recommendation-tribunal/aggregate.sh (deterministic, no LLM). Apply vetos.
  5. Decide final verdict: PASS / WARN / VETO.
  6. Persist audit trail via output/recommendation-tribunal/<date>/<hash>.json.
  7. Return structured JSON: {verdict, judges, banner, audit_path}.
  8. Hard timeout 3s wall-clock. If exceeded → return {"verdict":"WARN","reason":"timeout"} with whatever partial verdicts arrived. NEVER block the turn entirely.

Veto rules (any triggers VETO)

  • Any judge with confidence ≥ 0.8 AND veto: true.
  • memory-conflict on feedback_* or user_* memory file (semantic match, not just substring).
  • rule-violation on Rule #1 (PAT hardcoded), Rule #8 (agent without spec), autonomous-safety.md, or radical-honesty.md.
  • hallucination-fast with ≥1 fabricated entity at confidence ≥ 0.9.

Output format (always JSON)

{
  "verdict": "PASS|WARN|VETO",
  "draft_hash": "sha256:...",
  "judges": {
    "memory-conflict": {"score": int, "veto": bool, "reason": "...", "evidence": [...]},
    "rule-violation": {"score": int, "veto": bool, "rules_hit": [...]},
    "hallucination-fast": {"score": int, "veto": bool, "fabricated": [...]},
    "expertise-asymmetry": {"score": int, "audit_level": "blind|low|medium|high", "mode": "normal|rewrite-blind"}
  },
  "banner": "string (markdown, empty if PASS)",
  "audit_path": "output/recommendation-tribunal/YYYY-MM-DD/<hash>.json",
  "latency_ms": int
}

Read the full file on GitHub · 86 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 86 lines · 43 tokens per session scan A c28d6848b028

Subscribe to this mod's changes

recommendation-tribunal-orchestrator is an agent published in the GitHub repository gonzalezpazmonica/pm-workspace (49 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 1,132 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to recommendation-tribunal-orchestrator, differing in 0 lines, and is treated as a copy.