Borrowing it
Nothing to install: this file belongs to egregore-labs/egregore. 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/egregore-labs/egregore/main/.claude/skills/meeting/SKILL.mdgit clone --depth 1 https://github.com/egregore-labs/egregoreWrote 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/egregore-labs/egregore/meeting)<a href="https://agentmods.dev/skills/egregore-labs/egregore/meeting"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/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/egregore-labs/egregore/meeting"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/meeting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 Agent Snooping · line 294 Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
- high Agent Snooping · line 300 Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
- high System Prompt Leakage · line 474 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- high Anti-Refusal · line 916 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00041 | $0.10334 |
| Opus 5 | $0.00020 | $0.05167 |
| Sonnet 5 | $0.00008 | $0.02067 |
| Haiku 4.5 | $0.00004 | $0.01033 |
Grade A, and why
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 11d 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 — 1,046 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze meetings from Granola. Adaptive approach — the agent reads the material, asks what matters, and decides how to analyze.
When to invoke
User says: "/meeting" (list unprocessed meetings), "/meeting sync" (process all), "/meeting [search]" (find and process a specific meeting), "/meeting backfill" (re-process historical meetings with richer extraction).
Arguments: $ARGUMENTS (Optional: "sync" for batch mode, "backfill" to re-process historical meetings, or search term to find a specific meeting)
Usage
/meeting— Interactive: list recent unprocessed meetings, pick one/meeting sync— Batch: process all unprocessed meetings/meeting [search]— Find and process a specific meeting by title/meeting backfill— Re-process already-ingested meetings with richer extraction
Orientation
Three principles, not fixed constraints:
- The user knows what matters — ask before analyzing. "Just give me the action items" and "help me understand the political dynamics" should produce fundamentally different analyses.
- The material tells you how to read it — let inputs shape approach. A 10-minute standup and a 90-minute strategy session call for different depth.
- The output schema is the only constraint — everything else is yours to decide. The graph needs structure to index against. Everything between "load context" and "write files" is the free zone.
The output schema exists because the graph needs structure. Everything between "load context" and "write files" is yours.
You are the analyst. The meeting is your material. The user is your client. The graph is your institutional memory. Do good work.
Intent Harvesting
Before you touch the transcript, ask the user what they need.
Use 2-3 quick AskUserQuestion prompts, adapted to context — not a fixed questionnaire. Examples:
- What matters most from this meeting?
- Full depth or quick extraction?
- Connect to prior threads or fresh analysis?
- Anything I should know going in?
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.
- 11d ago First seen · 1,046 lines · 41 tokens per session scan A a84d971f5531
meeting is a skill published in the GitHub repository egregore-labs/egregore (288 stars, last pushed 7d ago), licensed MIT. It adds 41 tokens to every session and 10,334 once invoked, about $0.0002 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
memory-promote
Promote a personal-scope session learning into team scope through curated review. Strips private-tagged content and secret-shaped strings, then produces a reviewable artifact (PR-style proposal) instead of writing shared memory directly. Use when a personal memory note is worth sharing with the team. Enforces…
atlas-sync
Restore project context after clear/new session by following the canonical sync command doc.
neat-freak
Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and…
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.
install
Install the Rekal binary on this machine. Use when rekal is not on PATH — a command reported command not found — or when the user asks to install Rekal. Once per machine, not per repository; to set up a repo that already has the binary, use the init skill instead.
sw-do
Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".