- name
SKILL.md
स्किल फ़ाइल पब्लिशर की रिपॉज़िटरी में ही रहती है।
कॉपी की गई कमांड टर्मिनल में पेस्ट करें। यह इस SKILL.md को उस एजेंट में इंस्टॉल करती है।
npx skills add glebis/claude-skills --skill agent-roundtable -a cursor -yकॉपी की गई कमांड टर्मिनल में पेस्ट करें। यह इस SKILL.md को उस एजेंट में इंस्टॉल करती है।
npx skills add glebis/claude-skills --skill agent-roundtable -a claude-code -yकॉपी की गई कमांड टर्मिनल में पेस्ट करें। यह इस SKILL.md को उस एजेंट में इंस्टॉल करती है।
npx skills add glebis/claude-skills --skill agent-roundtable -a codex -yकॉपी की गई कमांड टर्मिनल में पेस्ट करें। यह इस SKILL.md को उस एजेंट में इंस्टॉल करती है।
npx skills add glebis/claude-skills --skill agent-roundtable -a grok -yकॉपी किया गया संदेश Grok Bot चैट में भेजें। Bot यह SKILL.md GitHub से लाता है और उसे उन स्किल में जोड़ देता है जो आपके सभी Bot साझा करते हैं।
Install this skill: https://github.com/glebis/claude-skills/tree/HEAD/agent-roundtableपब्लिशर से
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.
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".
Before anything else, ask through cenno (mcp__cenno__ask_user, choice):
--mode active.--mode auto.The answer decides what you ask next. For result only, ask nothing else that has a sensible default: pick format, agents, rounds and output yourself and state the choices in one line. For hands-on, confirm the format and agents in one mcp__cenno__ask_sequence.
Write brief.md in the run directory with: Target, Type, Goal of the audit, Scope (in and out), How to verify (test commands), and Known context the agents cannot discover (business constraints, user intent). Keep it under ~150 lines and point to files instead of pasting them; the agents can read the repo.
Read references/formats.md. Short version:
Default agents: codex,cmd. Add claude when a third view helps: it is a separate Claude session with its own context, but the same model family as you, so it adds no model diversity. Add opencode/gemini only when they pass doctor.
Use setup when the user asks to choose models, or before the first run when they want explicit model choices. In a terminal:
node ~/.claude/skills/agent-roundtable/scripts/roundtable.mjs setup --agents codex,cmd,claude
When orchestrating through tools rather than a terminal, discover with setup --agents codex,cmd,claude --json, present the advertised names and IDs through cenno, then save their choices:
node ~/.claude/skills/agent-roundtable/scripts/roundtable.mjs setup \
--agents codex,cmd --models 'codex=MODEL_ID,cmd=MODEL_ID'
Replace MODEL_ID with the exact IDs from discovery. --models 'codex=@default' clears an override. Selections are saved atomically to <cwd>/.roundtable.json; use --cwd TARGET to configure a particular target or --config FILE to share an explicit configuration. Pass the same --config to run/doctor when using a custom file. Discovery-only --json does not save anything.
Run and doctor load the saved choices. ACP validates each model against advertised options and confirms the setter response before any turn; every restarted session reapplies it. Headless initial/resume commands receive the same model through --model. Unsupported or rejected choices fail visibly, never silently select an alternative. State/result record requested and effective models where reported. Setup discovery is not proof that live inference with the model will succeed.
Then check every agent over its live transport:
node ~/.claude/skills/agent-roundtable/scripts/roundtable.mjs doctor
doctor starts every agent over its default transport and sends a one-line prompt, so expired keys and failed logins show up here, not in round 1. The other transport is only started. Drop agents whose default transport fails and whose other transport doesn't start, and tell the user which and why. Known traps: gemini ACP needs a working Google OAuth login (gemini interactively once); opencode connects but fails at the first prompt when its API key is expired. First install: cd ~/.claude/skills/agent-roundtable/scripts && npm install.
node ~/.claude/skills/agent-roundtable/scripts/roundtable.mjs run \
--brief RUN/brief.md --run-dir RUN --cwd TARGET_REPO \
--agents codex,cmd --format panel --rounds 3 --mode auto
Use RUN = <target repo>/docs/roundtable/<slug>-<YYYY-MM-DD>/ when the user wants a handoff doc, otherwise the scratchpad. RUN must be fresh: the runner refuses a directory that already has state.json, moderator/ or synthesis.md. Start it with run_in_background: true and watch RUN/state.json with Monitor (an until-loop on its status field), never with bare sleeps.
Options: --rounds (default 3), --min-rounds (default 2), --turn-timeout seconds per agent turn (900), --budget-min wall clock for the debate (60), --transport auto|acp|headless (auto = each agent's default), --roles a,b for the roles format, --no-veto, --drain-timeout (30) and --kill-grace (5) seconds, --registry for another agents.json, --config for another model-selection file.
Read-only is best effort. Agents may read anything and run commands. The ACP permission rule decides by path, never by the tool's title:
read, search, fetch, think, execute anywhere; edit/delete/move/other when every location is outside the target and the run dir (scratch files in /tmp are fine);edit/delete/move without locations, a missing or unknown kind, switch_mode.Headless agents run under their CLI's own guard (codex --sandbox read-only, cmd and claude --permission-mode plan). After every round and after the veto the runner compares a content fingerprint of the target (tracked diff plus untracked files, run dir excluded; gitignored files are not covered) and adds a warning to state.json if it changed. Report any such warning to the user.
Failed turns and degraded runs. A turn fails when the agent crashes, hangs, times out, or stops with anything other than end_turn. On a timeout the runner cancels the turn and waits up to 30 s for it to stop; otherwise it kills the agent, so a late reply can't leak into the next turn. Each agent gets 3 failed attempts over the whole run:
rounds/ replies, and re-run the turn;A failed agent's vote is cleared at once. A switch or a drop makes the run degraded: state.result is degraded, state.degraded names who and what, and the consensus reason says so. Never present a degraded run as full consensus.
Write every file you hand to the runner atomically: write moderator/rN.md.tmp (or synthesis.md.tmp), then mv it to the final name. The runner reads only the final name.
| veto/<agent>.md, veto.json | runner | each agent's approve/object on the draft |
| events.log | runner | transport choices, tool calls, permission decisions, failures |
When status is awaiting_moderator (active mode), read the round's replies and summary, then:
moderator/rN.md. Moderate the process (which disagreements to settle, what evidence is missing), do not argue a side.In auto mode the runner detects deadlock itself: when the same set of blocking ids holds two rounds running, it switches to awaiting_moderator (with waitingReason: deadlock …) even in auto mode. Read the two rounds, ask the user through cenno if it needs a human call, and write moderator/rN.md: which disagreement to settle and what evidence would settle it, or STOP. You may also drop a note in auto mode without being asked; it is picked up at the start of the next round.
When status is awaiting_synthesis, write synthesis.md using references/output-template.md. Rules that keep your bias in check:
The runner sends the draft to every live agent, together with every agent's final-round status and a short summary of its last reply, so a veto is judged against where the debate actually ended. If veto.json has an objection, fix what it points to (or move it into Open disagreements), write a short note of what changed, and finalize. Do not run a second veto round unless the user asks.
Ask (or, in result-only mode, use what the user said earlier) where the result goes:
synthesis.md saved as RUN/final.md in the target repo, linked in your reply.Always end with: agents and transports used (and any switch or drop), state.result, rounds run and why it stopped (state.stopReason), veto results, and any warnings.
agents.json: default transport, acp command, headless.start/headless.resume argv with {out}, {cwd}, {session}, {promptFile} placeholders, input (stdin or file) and output (codex-jsonl, json), optional authMethod (used only when session/new fails with the auth-required code and the agent advertises that method). Add an ACP agent by adding an entry.cd scripts && npm test. They drive the real ACP SDK against a fake agent (scripts/test/fake-agent.mjs) and a fake resumable CLI.scripts/consensus.mjs, assessConsensus(statuses, ctx).roundtable-status block format are in scripts/prompts.mjs.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
---name: agent-roundtabledescription: Run a multi-agent audit of a feature, PR/diff, or task spec in which Codex, Command Code (cmd), Gemini…---# agent-roundtable/SKILL.mdओवरव्यू
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", "multi-agent review", "council", or wants several coding agents to agree on a spec.
FAQ
पब्लिशर से agent-roundtable/SKILL.md डाउनलोड करें, या पाथ कॉपी करके रिपॉज़िटरी खोलें। PlugMCP स्किल को सूचीबद्ध करता है, फ़ाइल होस्ट नहीं करता।
पब्लिशर इसे https://github.com/glebis/claude-skills पर रखता है।
Claude, Cursor, Codex और Grok Build वह SKILL.md पढ़ सकते हैं जिसे आप पब्लिशर की रिपॉज़िटरी से जोड़ते हैं। जब आप चैट में स्किल के GitHub फ़ोल्डर का लिंक भेजते हैं, तो Grok Bot उसे इंस्टॉल कर देता है।