What is meeting-copilot?

A live meeting assistant that uses two computers: one captures the meeting audio and another transcribes it, monitors agreed facts, and shows prompts. A teleprompter is an on-screen script that guides what you say during the meeting.

Guiding a meeting agenda, checking statements against agreed facts, answering unexpected questions, and displaying prepared responses. It is designed for meetings where one Windows laptop captures the audio and a parent computer handles the processing.

It separates your voice from the other speaker's voice using audio channels and watches for contradictions or new information. It also keeps private prompts separate from the window shared with participants.

meeting-copilot — Skill for Codex by yohey-w

Install

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.

Clone the repo

git clone --depth 1 https://github.com/yohey-w/kagemusha

agentmods

npx agentmods add skills/yohey-w/kagemusha/meeting-copilot

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yohey-w/kagemusha/meeting-copilot/github.svg)](https://agentmods.dev/skills/yohey-w/kagemusha/meeting-copilot)

Your own site

<a href="https://agentmods.dev/skills/yohey-w/kagemusha/meeting-copilot"><img src="https://agentmods.dev/badge/skills/yohey-w/kagemusha/meeting-copilot/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yohey-w/kagemusha/meeting-copilot"><img src="https://agentmods.dev/badge/skills/yohey-w/kagemusha/meeting-copilot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 225 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 16,604 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 3 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 YARA Match · line 82
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
medium Rogue Agent · line 346
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.
medium Rogue Agent · line 416
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.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00225	$0.16604
Opus 5	$0.00112	$0.08302
Sonnet 5	$0.00045	$0.03321
Haiku 4.5	$0.00022	$0.01660

Measured 5d ago against content hash 4a0d176441df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

meeting-copilot scanned grade A with 1 finding 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 5d ago.

The scan reads SKILL.md. This mod also ships 28 executable files (scripts/action_log.py, scripts/agent_cli.py, scripts/answerer.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| `viewer2.py` | `curl http://127.0.0.1:47323/quit` してから新しいのを起動 | `/quit` は**localhost からのみ**受け付け、0.3秒後に自ら終了する。外から止められると会議中に事故るのでこの制限がある |

templates/skills/meeting-copilot/SKILL.md · 856 lines

How it starts

The opening of the file, as written. The whole thing — 856 lines — stays where its author put it; the contents beside it link to each section on GitHub.

meeting-copilot

会議に同席して、進行と前提を見張るモニタ一式

English abstract — Two machines. The child (a Windows laptop, in the meeting) captures two physical audio channels — T = your microphone, G = a WASAPI loopback of the default speaker — and streams both to the parent over TCP with a shared token. The parent transcribes each channel separately (speaker identity comes from the channel, never from diarization), then runs three layers over the transcript: a rule-only warden (copilot.py) that advances the agenda and fires boundary alarms with no LLM at all; a premise watcher (premise_watch.py) that classifies every guest utterance against a ledger of pre-agreed facts as contradiction / already-known / new; and an answerer (answerer.py) for off-script questions. A teleprompter (viewer2.py) serves two different pages — a prompt screen only you see on your phone, and a stage window you actually screen-share. Everything case-specific lives in config files; the code carries no customer data. Written mainly in Japanese; the structure is language-independent.

0. 全体像 — これは2台構成である

一番よくある取り違えが「1台で完結する道具だと思う」こと。必ず2台要る。

┌─ 子機 (Windows ノートPC・会議に持っていく機体) ────────────┐
│                                                              │
│   マイク ────────────► agent_mic.py  ──┐  ch "T"            │
│                                          │                   │
│   既定スピーカーの                       │                   │
│   ループバック ─────► agent_loop.py ──┤  ch "G"            │
│                                          │                   │
│   音を録って送るだけ。STTもAPIキーも持たない                │
└──────────────────────────────────────────┼──────────────────┘
                                            │
                   TCP + 合言葉(token)      │  16kHz mono ×2本
                   プライベート網(tailscale等)を想定
                                            │
┌─ 親機 (Linux / WSL・自宅や事務所に置きっぱなし) ───────────┼───┐
│                                            ▼                    │
│   receiver.py  … 音を受けて STT へ流し transcript.jsonl へ追記 │
│        │                                                        │
│        ├──► copilot.py       … ルールだけで段の進行・境界警報   │
│        │        ├──► premise_watch.py … 相手の発話×事実台帳     │
│        │        └──► answerer.py      … 台本外の質問に回答      │
│        │                                                        │
│        └──► viewer2.py       … カンペ画面 + 舞台画面を配信      │
└─────────────────────────────────────────────────────────────────┘
        │                              │
        │ カンペ画面(自分だけ見る)     │ 舞台画面(相手に画面共有する)
        ▼                              ▼
    スマホ / 携帯ディスプレイ      名前付き別窓 meetlive_stage

Read the full file on GitHub · 856 lines

Files

What ships with it

46 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

5d ago Changed · +16 lines 4a0d176441df
8d ago Changed · +186 lines 491e7223c240
12d ago First seen · 654 lines · 225 tokens per session scan A 51f510600a1f

Subscribe to this mod's changes

meeting-copilot is a skill published in the GitHub repository yohey-w/kagemusha (9 stars, last pushed today), licensed MIT. It adds 225 tokens to every session and 16,604 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Productivity agent-governance ai-agents approval-workflow human-in-the-loop loop-engineering

save-progress

Save current project task progress to local task state file for cross-session continuity. Use when the user asks to save progress, uses an equivalent localized trigger phrase, the session is interrupted, or the user wants to resume work later. Writes to .claude/project-task-state.json so next session can load it via…

KimYx0207/Meta_Kim · 65 tokens

e2a

Use when operating an already-connected e2a inbox over MCP: reading, composing, sending, replying, forwarding, handling attachments, managing contacts/outreach, scheduling mail, or using templates. Teaches correct threading, conversation correlation, concise multipart composition, and accepted/pending-review no-retry…

tokencanopy/e2a · 64 tokens

meeting-copilot

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Makes network callslowCapability

How it starts

meeting-copilot

0. 全体像 — これは2台構成である

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

save-progress

e2a

script.automate

social.reply

feishu-interaction

calendar-event-create