Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/LiXin97/agora-labnpx agentmods add skills/lixin97/agora-lab/supervisor-meetingWrote 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/lixin97/agora-lab/supervisor-meeting)<a href="https://agentmods.dev/skills/lixin97/agora-lab/supervisor-meeting"><img src="https://agentmods.dev/badge/skills/lixin97/agora-lab/supervisor-meeting/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/lixin97/agora-lab/supervisor-meeting"><img src="https://agentmods.dev/badge/skills/lixin97/agora-lab/supervisor-meeting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00016 | $0.00568 |
| Opus 5 | $0.00008 | $0.00284 |
| Sonnet 5 | $0.00003 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
supervisor-meeting 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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Supervisor Meeting
Use this with core-meeting.
Responsibilities
- create the meeting
- keep discussion focused on decision-relevant evidence
- advance phases only when the current one is truly ready
- write
decision.md - convert decisions into concrete next tasks
- set agenda framing in
agenda.md
Phase Advancement Rule (IMPORTANT)
You own phase advancement. Do not wait for anyone to ask. Advance the moment the current phase's artifact set is complete:
- PREPARE done when every participant has a file in
perspectives/. Then advance to CROSS-READ. - CROSS-READ done when every participant has ack-read (or you've waited a reasonable window after posting ack reminders). Then advance to CHALLENGE.
- CHALLENGE done when every participant who intends to critique has filed in
critiques/. You do not need a critique from every participant on every other participant — a quorum of non-trivial critiques (typically ≥ N-1 files) is enough. Then advance to RESPOND. - RESPOND done when each critiqued participant has either filed a
responses/*_response.mdor explicitly declined via message. Then advance to DECISION. - DECISION: you write
decision.mdand-completethe meeting.
Judgments (judgments/) are written by staff and you throughout the meeting; they are not a phase-gate. Do not hold a phase waiting for peer judgments.
If you find yourself thinking "I'm waiting for X before I advance," check whether X is actually a phase-gate above. If not, advance now.
Required Commands
bash ../../scripts/lab-meeting.sh -caller <your-name> -new
bash ../../scripts/lab-meeting.sh -caller <your-name> -phase <phase-name>
bash ../../scripts/lab-meeting.sh -caller <your-name> -auto
bash ../../scripts/lab-meeting.sh -caller <your-name> -auto-advance [-timeout 1800] [-interval 30]
bash ../../scripts/lab-meeting.sh -caller <your-name> -check-ready
bash ../../scripts/lab-meeting.sh -caller <your-name> -ack-read
bash ../../scripts/lab-meeting.sh -caller <your-name> -complete
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.
- 10d ago First seen · 52 lines · 16 tokens per session scan A 53b82f513ebb
supervisor-meeting is a skill published in the GitHub repository LiXin97/agora-lab (49 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 568 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
compact-now
Operator-triggered proactive compaction — Chrono externalizes load-bearing state (active decisions, open tasks, next action) to a snapshot + a durable Vault learning note before invoking Claude Code's native /compact, then resumes from the snapshot. Use when the operator says "/compact-now" / "compact now" or when…
claude-code-expert
Especialista profundo em Claude Code - CLI da Anthropic. Maximiza produtividade com atalhos, hooks, MCPs, configuracoes avancadas, workflows, CLAUDE.md, memoria, sub-agentes, permissoes e integracao com ecossistemas.
openrig-herdr
Use when opening OpenRig fleet terminals as a herdr wall — turning a rig, pod, mission, slice, or saved view into live interactive agent tiles via rig terminal, watching another rig read-only, or driving herdr on an agent's request ("open all my rigs + a mission as views"). Covers the rig terminal open|views|status…
slack
Read bounded Slack search and thread evidence, plan an exact reply, and deliver an approved reply through any compatible Slack binding with stable-message readback.
operator-inbox
Maintain a provider-neutral local action queue from bounded provider observations and explicit human dispositions.