agent-roundtable SKILL.md skillA

agent-roundtable from glebis/claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add glebis/claude-skills/agent-roundtable@git:20261102.1dd68ce

Pins git:20261102.1dd68ce in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
glebis/claude-skills
Path
agent-roundtable/SKILL.md
Versions recorded
3
Latest version
git:20261102.1dd68ce, committed Nov 2, 2026
First version recorded
Oct 25, 2026
Size
12,991 bytes
Repository stars
410
License
MIT

Run a multi-agent audit of a feature, PR/diff, or task spec in which Codex, Command Code (cmd), Gemini, OpenCode and Claude debate over ACP for a configurable number of rounds and converge on a final spec, a prioritized task list and improvements. Claude moderates and synthesizes; every other agent gets a final veto. Use when the user says "roundtable", "agent roundtable", "audit this with codex", "have the agents discuss/debate this", "get a second (third) opinion from other agents…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Agent Roundtable

A moderated debate between coding agents that ends in one agreed spec. You (Claude, the orchestrating session) are the **moderator and synthesizer**, not a debater. The runner `scripts/roundtable.mjs` keeps one continuous conversation per debating agent, over one of two equal transports, and recovers an agent that dies or hangs.

| Transport | How a turn runs | Memory across rounds | Default for |
|---|---|---|---|
| **ACP** (Agent Client Protocol) | one live session per agent; one reader per turn | the ACP session | `cmd`, `claude`, `gemini`, `opencode` |
| **headless** | one CLI call per turn, prompt over stdin | native resume by explicit session id (`codex exec resume <id>`, `cmd --resume <id>`, `claude -p --resume <id>`) | `codex` (with `--sandbox read-only`) |

`cmd` and `claude` run headless with `--permission-mode plan`. `gemini` and `opencode` have no headless adapter, because their CLIs can't resume a session by id. The runner never resumes "the latest session".

## 0. First question: how involved does the user want to be?

Before anything else, ask through cenno (`mcp__cenno__ask_user`, choice):
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add glebis/claude-skills/agent-roundtable@sha256:15ee879bca44afd7

The line at the top of this page pins the label git:20261102.1dd68ce, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_hxjanelg5to3vvki.svg)](https://markdownregistry.com/a/art_hxjanelg5to3vvki)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Oct 25, 2026 and Nov 2, 2026, about one every 4 days.

versioncommittedcommitsizeaudit
git:20261102.1dd68ce latest2026-11-02 1dd68ce 12,991 BA view · diff
git:20261025.d824f5a2026-10-25 d824f5a 11,440 BA view · diff
git:20261025.118a66a2026-10-25 118a66a 7,374 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (12991 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

glebis/claude-skills · 410 stars · license MIT · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_hxjanelg5to3vvki
GET https://markdownregistry.com/api/v1/resolve?ref=glebis/claude-skills/agent-roundtable
GET https://markdownregistry.com/api/v1/blob/15ee879bca44afd7260650f099784695fc837fc87ba2813273ec0b67521e6bb4

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from glebis/claude-skills

agency-docs-updater SKILL.md skill
glebis/claude-skills · agency-docs-updater/SKILL.md · End-to-end pipeline for publishing Claude Code lab meetings. Accepts optional args: date (YYYYMMDD, "yesterday"…
git:20261102.a1ab791 · audit B · 410 stars
agency-meetup-publish SKILL.md skill
glebis/claude-skills · agency-meetup-publish/SKILL.md · End-to-end pipeline for publishing AGENCY Community meetup recordings to YouTube. Downloads Zoom recording, adds…
git:20260529.9537db9 · audit A · 410 stars
agency-socials SKILL.md skill
glebis/claude-skills · agency-socials/SKILL.md · Generate social media covers and assets for AGENCY Community events, meetups, and YouTube recordings. Use when creating…
git:20260529.9537db9 · audit A · 410 stars
agent-cli SKILL.md skill
glebis/claude-skills · agent-cli/SKILL.md · Add agent-friendly --json NDJSON output to Python CLI scripts, or scaffold a complete cli_utils package for a project…
git:20260601.3bcdf69 · audit A · 410 stars
app-map SKILL.md skill
glebis/claude-skills · app-map/SKILL.md · This skill should be used when mapping an application's screens, workflows and tests into one interactive page. It…
git:20261105.a4aab52 · audit A · 410 stars
app-release SKILL.md skill
glebis/claude-skills · app-release/SKILL.md · End-to-end pipeline for releasing an iOS / watchOS app to TestFlight and the App Store. Use when the user wants to…
git:20260618.3a8359f · audit A · 410 stars
CLAUDE.md@automation-advisor CLAUDE.md file
glebis/claude-skills · automation-advisor/CLAUDE.md
git:20260124.90978aa · audit A · 410 stars
automation-advisor SKILL.md skill
glebis/claude-skills · automation-advisor/SKILL.md · Interactive automation decision advisor using the Automation Decision Matrix framework. Use when the user asks "should…
git:20260713.b688bbd · audit A · 410 stars
background-agents SKILL.md skill
glebis/claude-skills · background-agents/SKILL.md · Configure and run background agents with reusable profiles for agent engines, model providers and execution backends…
git:20261027.046a4ce · audit A · 410 stars
balanced SKILL.md skill
glebis/claude-skills · balanced/SKILL.md · Constructive, evidence-based dialogue mode that avoids sycophancy. This skill should be used when the user wants…
git:20261102.a5ce592 · audit A · 410 stars
brand-agency SKILL.md skill
glebis/claude-skills · brand-agency/SKILL.md · Applies Agency brand colors and typography to artifacts including presentations, SVG graphics, documents, and web…
git:20251129.852e17d · audit A · 410 stars
browser-mate SKILL.md skill
glebis/claude-skills · browser-mate/SKILL.md · Use when automating a real, logged-in Chrome WITHOUT disturbing the user's open tabs — e.g. authenticated sessions like…
git:20260603.90dabb0 · audit A · 410 stars

Every file in glebis/claude-skills

Browse by kind, by grade A, or by owner.