roundtable

roundtable is a skill for Codex from Smart-AI-Memory/attune-ai. It costs 59 tokens per session (4,312 once invoked), scanned A, original, Apache-2.0.

A moderated discussion in which Claude, Antigravity, and Codex independently consider a question and their answers are combined.

In plain words
What is it for?
Use it to compare approaches, examine a difficult decision, or ask multiple AI models to deliberate on a coding question.
Why use it?
It gives you several model opinions in one discussion while keeping you in control of what, if anything, is saved as a tracked file.

Skill for Codex

Written for Codex: runs codex exec. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

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.

agentmods
npx agentmods add skills/smart-ai-memory/attune-ai/roundtable
Any agent
npx skills add Smart-AI-Memory/attune-ai --skill roundtable
Clone the repo
git clone --depth 1 https://github.com/Smart-AI-Memory/attune-ai

Made for: Codex.

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 roundtable

README.md
[![agentmods](https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/roundtable.svg)](https://agentmods.dev/skills/smart-ai-memory/attune-ai/roundtable)
Your own site
<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/roundtable"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/roundtable.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,312 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00059 $0.04312
Opus 5 $0.00030 $0.02156
Sonnet 5 $0.00012 $0.00862
Haiku 4.5 $0.00006 $0.00431

Measured 2d ago against content hash 2a73a75b3008, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

roundtable 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 2d 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/skills/roundtable/SKILL.md · 370 lines

How it starts

The opening of the file, as written. The whole thing — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Round Table

IMPORTANT: Start your response by telling the user:

Round table — Convening the fixed roster (Claude, Antigravity, Codex). You chair; I moderate. Up to 3 rounds.

What It Does

A moderated deliberation (Phase 1 of docs/specs/agent-round-table): the user poses a question, each roster member answers headlessly and independently, the moderator (this session) posts every message to the Redis board, synthesizes, and presents the result. Only the chair — the user — promotes anything into a tracked artifact.

Invariants (ratified — do not improvise around them):

  • R1 Members are text-in/text-out. They never touch Redis, files, or shell. All board I/O goes through the moderator via the Board client (attune.roundtable).
  • R3 Board state lives only under attune:roundtable:* (TTL 7 days). Never write attune:memory:*.
  • R4 Nothing reaches a tracked file without explicit per-item chair approval. No auto-promotion, ever.
  • D3 Hard ceiling: 3 rounds per question. Halt early when positions converge or a round adds no information.

Shared command workspace (preferred)

When the generic command-workspace tools are available, use them as the chair-facing surface for the lifecycle below. They do not replace the board or grant seats new authority:

  1. Open adapter roundtable with command_workspace_open, passing the question, thread slug, expected rounds, and maximum seat invocations.
  2. Present its widget, or its returned Markdown verbatim when widgets are unavailable. Collect only bound chair actions through command_workspace_collect_action.
  3. After the existing moderator-only compiler and board operations succeed, publish seat_progress, round_complete, and synthesis events through command_workspace_publish. A compiler-dirty reply is never published.
  4. Render promotion triage in atomic batches of at most three candidates. Each accepted apply_rulings batch advances one revision; a prior page is stale. Seven candidates complete in 3 + 3 + 1. Retain the one-candidate promote / decline actions as the compatibility fallback.

Read the full file on GitHub · 370 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. 2d ago Changed · +34 lines 2a73a75b3008
  2. 6d ago First seen · 336 lines · 59 tokens per session scan A 79b537d3b7b4

Subscribe to this mod's changes

roundtable is a skill published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed today), licensed Apache-2.0. It adds 59 tokens to every session and 4,312 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

tmux

Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).

Team-Commonly/commonly · 48 tokens

lynkr

Universal LLM gateway with intelligent routing, Graphify code intelligence, Distill compression, routing telemetry, Code Mode, and 12+ provider support. 60-80% cost reduction for Claude Code, Cursor, and Codex.

Fast-Editor/Lynkr · 50 tokens

web-research

Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research.

shibing624/agentica · 24 tokens

story-setup

网文写作工具集基础设施部署。将 hooks/rules/agents/CLAUDE.md/AGENTS.md 等基础设施部署到用户项目目录,支持 Claude Code / OpenCode / Codex / OpenClaw。触发方式:/story-setup、$story-setup、「准备写书」「帮我搭一下环境」「配置写作项目」。.

Xiaoyangy/novel-studio · 81 tokens

novel-writing-assets

查看、启用、停用、组合、绑定、试写和重新编译 novel-studio 的长期写法资产。触发:「列出写法特征」「启用/停用某个写法」「组合写法」「绑定写法」「试写写法」「重编译写法规则」「维护写法资产」。.

Xiaoyangy/novel-studio · 77 tokens

officecli

Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.

Team-Commonly/commonly · 56 tokens