Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/onlyterp/hermes-optimization-guide/meeting-prepnpx skills add OnlyTerp/hermes-optimization-guide --skill meeting-prepgit clone --depth 1 https://github.com/OnlyTerp/hermes-optimization-guideWrote 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/onlyterp/hermes-optimization-guide/meeting-prep)<a href="https://agentmods.dev/skills/onlyterp/hermes-optimization-guide/meeting-prep"><img src="https://agentmods.dev/badge/skills/onlyterp/hermes-optimization-guide/meeting-prep.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.00826 |
| Opus 5 | $0.00014 | $0.00413 |
| Sonnet 5 | $0.00005 | $0.00165 |
| Haiku 4.5 | $0.00003 | $0.00083 |
Grade A, and why
meeting-prep 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 5d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
meeting-prep — Pre-Meeting Brief
Produces a one-page markdown brief so you walk into meetings knowing what's going on.
Output shape
## Meeting: {title}
**When:** {datetime} · **Duration:** {duration} · **Where:** {location}
**Attendees:** {list with titles where known}
### Context
- Last topic we discussed: {summary}
- Open asks from them: {list}
- Open asks from me: {list}
### Likely agenda
1. {item}
2. {item}
### My position / notes
{bulleted; pulled from memory if relevant}
### Warnings
- {anything they sent recently that suggests a tough topic}
### Quick links
- [last email thread]({url})
- [shared doc]({url})
- [previous meeting notes]({memory-link})
Procedure
-
Resolve meeting from
lookup::- "next" → next calendar event in personal calendar
- a time → nearest event at that time
- a person → next event where that person is an attendee
- event id → that exact event
-
Gather (parallel):
- Last 10 emails with each attendee (last 90 days)
- Last Slack DMs / channel mentions with each attendee (last 30 days)
- Relevant docs from memory (
/searchwith meeting title + attendee names) - Previous meeting notes if exist in memory
-
Summarize each thread to 1–2 lines. Extract open asks (things needing response, either direction).
-
Produce the brief. Keep under 400 words. Bias for brevity — this is a read-in-60-seconds doc.
-
Attach the brief as a Telegram DM reply to the trigger event, or print to CLI if invoked there.
Triggering 15 min before each meeting
Cron jobs live in ~/.hermes/cron/jobs.json, created via hermes cron create. The old YAML cron list (and its filter: field) was removed
upstream — the cheapest honest pattern is a short-interval job that runs
the skill and lets it decide whether a meeting is <15m away (the skill
queries your calendar anyway):
hermes cron create "*/5 * * * *" \
"Prep for the next meeting if it starts within 15 minutes and is tagged prep:true" \
--skill meeting-prep --name meeting-prep --deliver telegram
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 First seen · 101 lines · 27 tokens per session scan A 6a79d50ff5f8
meeting-prep is a skill published in the GitHub repository OnlyTerp/hermes-optimization-guide (629 stars, last pushed 8d ago), licensed MIT. It adds 27 tokens to every session and 826 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.