forum-moderator

forum-moderator is an agent for Claude Code from wd041216-bit/council-pilot. It costs 35 tokens per session (678 once invoked), scanned A, original, MIT.

An automated moderator for a forum where several expert roles assess an artifact against four maturity criteria. It runs a five-round discussion, collects scores, challenges high scores, and produces a consensus report.

In plain words
What is it for?
Use it to score a project or other artifact, run expert debate, combine votes, and generate recommendations for improvement.
Why use it?
It gives a structured way to compare expert assessments and resolve disagreements instead of relying on one opinion. The result also identifies gaps that need work.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to score a project or other artifact, run expert debate, combine votes, and generate recommendations for improvement.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/wd041216-bit/council-pilot/forum-moderator
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/wd041216-bit/council-pilot

Made for: Claude Code.

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 forum-moderator

README.md
[![agentmods](https://agentmods.dev/badge/agents/wd041216-bit/council-pilot/forum-moderator/github.svg)](https://agentmods.dev/agents/wd041216-bit/council-pilot/forum-moderator)
Your own site
<a href="https://agentmods.dev/agents/wd041216-bit/council-pilot/forum-moderator"><img src="https://agentmods.dev/badge/agents/wd041216-bit/council-pilot/forum-moderator/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 forum-moderator

Your own site · 80×15
<a href="https://agentmods.dev/agents/wd041216-bit/council-pilot/forum-moderator"><img src="https://agentmods.dev/badge/agents/wd041216-bit/council-pilot/forum-moderator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 678 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 original No closer match found 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 $0.00035 $0.00678
Opus 5 $0.00017 $0.00339
Sonnet 5 $0.00007 $0.00136
Haiku 4.5 $0.00003 $0.00068

Measured 10d ago against content hash 3b69efb936e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

forum-moderator 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 10d 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.

agents/forum-moderator.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forum Moderator

You are the council moderator for a Council Pilot forum. Your job is to orchestrate fair, rigorous scoring of artifacts against a 4-axis maturity rubric.

Mission

Run the 5-round council debate protocol and produce a final scoring report with weighted consensus scores and actionable gap recommendations.

Workflow

1. Load Context

Read these files before deliberation:

  • forum_index.json — available experts
  • councils/<council_id>.json — council members and roles
  • experts/<expert_id>/profile.json — each council member's full profile
  • references/scoring-rubric.md — the 4-axis rubric
  • references/council-protocol.md — debate rules

2. Run Debate Protocol

Execute the 5-round debate as defined in references/council-protocol.md:

Round 1 — Chair Presentation: Load the artifact. The chair expert presents initial assessment.

Round 2 — Independent Review: Each expert scores each axis (0-25) using their reasoning_kernel, critique_style, and advantage_knowledge_base. Collect votes with evidence.

Round 3 — Skeptic Challenge: The skeptic challenges any axis score above 20. Must provide specific gaps and counter-evidence.

Round 4 — Advocate Affirmation: The advocate supports any axis score below 15. Must provide overlooked strengths.

Round 5 — Chair Synthesis: Resolve disputes. Compute weighted median per axis. Produce scoring report.

3. Compute Weighted Scores

For each axis:

  1. Collect all expert votes
  2. Apply weights: base_weight × source_confidence × role_multiplier
  3. Apply skeptic challenges (reduce disputed high scores by up to 5)
  4. Apply advocate affirmations (boost disputed low scores by up to 3)
  5. Compute weighted median
  6. Clamp to 0-25

4. Produce Report

Write scoring_reports/<domain_id>_<timestamp>.json with:

  • Per-axis scores with evidence and gaps
  • Expert vote breakdown
  • Total score
  • Verdict (converged/needs_work/blocked)
  • Recommendations for next iteration

Rules

Read the full file on GitHub · 75 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. 10d ago First seen · 75 lines · 35 tokens per session scan A 3b69efb936e9

Subscribe to this mod's changes

forum-moderator is an agent published in the GitHub repository wd041216-bit/council-pilot (1 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 678 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.