Borrowing it
Nothing to install: this file belongs to Smart-AI-Memory/attune-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Smart-AI-Memory/attune-ai/main/.agents/skills/roundtable/SKILL.mdgit clone --depth 1 https://github.com/Smart-AI-Memory/attune-aiWrote 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.
[](https://agentmods.dev/skills/smart-ai-memory/attune-ai/roundtable)<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/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.
<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="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Excessive Agency · line 111 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Rogue Agent · line 27 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.04312 |
| Opus 5.5 | $0.00024 | $0.01725 |
| Sonnet 5.5 | $0.00012 | $0.00862 |
| Haiku 4.5 | $0.00006 | $0.00431 |
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 1mo 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.
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
Boardclient (attune.roundtable). - R3 Board state lives only under
attune:roundtable:*(TTL 7 days). Never writeattune: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:
- Open adapter
roundtablewithcommand_workspace_open, passing the question, thread slug, expected rounds, and maximum seat invocations. - Present its widget, or its returned Markdown verbatim when widgets are
unavailable. Collect only bound chair actions through
command_workspace_collect_action. - After the existing moderator-only compiler and board operations succeed,
publish
seat_progress,round_complete, andsynthesisevents throughcommand_workspace_publish. A compiler-dirty reply is never published. - Render promotion triage in atomic batches of at most three candidates.
Each accepted
apply_rulingsbatch advances one revision; a prior page is stale. Seven candidates complete in3 + 3 + 1. Retain the one-candidatepromote/declineactions as the compatibility fallback.
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.
- 1mo ago Changed · +34 lines 2a73a75b3008
- 1mo ago First seen · 336 lines · 59 tokens per session scan A 79b537d3b7b4
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 $0.0002 per session on Opus 5.5. 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.
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).
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.
web-research
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research.
avalon-8-10p
Eight-to-ten-player Avalon rules for a permanent Agent host, with the user choosing to join the randomized player pool or spectate.
pptx
Instructions for reading, creating, and editing PowerPoint presentation files and templates, including .pptx, .potx, and older .ppt files. They cover text, tables, images, charts, layouts, and speaker notes.
docx
Instructions for safely reading, creating, and editing Microsoft Word documents and templates, including tables, images, comments, and tracked changes.