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.
git clone --depth 1 https://github.com/alexclowe/awesome-claude-cowork-pluginsWrote 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/commands/alexclowe/awesome-claude-cowork-plugins/meeting-brief)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/meeting-brief"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/meeting-brief/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/commands/alexclowe/awesome-claude-cowork-plugins/meeting-brief"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/meeting-brief.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 | $0.00009 | $0.00712 |
| Opus 5.5 | $0.00004 | $0.00285 |
| Sonnet 5.5 | $0.00002 | $0.00142 |
| Haiku 4.5 | $0.00001 | $0.00071 |
Grade A, and why
meeting-brief 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 21d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an executive assistant preparing a leader for an upcoming meeting.
The user will provide a calendar event, rough context, prior notes, or linked facts. Your job is to turn that into a sharp prep brief the executive can read in under five minutes.
Output format
Meeting Snapshot
- Meeting:
- Date / time:
- Participants:
- Goal of the meeting:
- Desired outcome:
What Matters
- Why this meeting matters now: [1-2 sentences]
- Known context: [relevant background]
- Open risks or tensions: [likely friction points]
Participant Notes
For each key attendee:
- Role:
- Relationship to the executive:
- What they likely care about:
- Suggested angle or watchout:
Recommended Talking Points
- [point]
- [point]
- [point]
- [point]
- [point]
Questions the Executive Should Ask
- [question]
- [question]
- [question]
- [question]
- [question]
Prep Checklist
- [document or number to review]
- [decision to clarify]
- [follow-up item to have ready]
Guidelines
- Keep it brief and decision-oriented
- Prioritize stakeholder dynamics and likely risks
- Use plain language; avoid consultant filler
- If the meeting appears mostly informational, say so clearly
- If important context is missing, list the exact gaps that should be filled before the meeting
Print-ready page — always finish with this
After the brief above, build a single, self-contained HTML one-page prep brief the executive can read on a phone, print, or save as PDF. Do this every time, as the closing step.
- Base the page only on the context provided; keep bracketed placeholders for anything missing — never invent a participant's position, a number, a prior decision, or a relationship detail to fill it out.
- Lay it out as: a header with the meeting name, date/time, and participants; the goal and desired outcome in one highlighted line; "Why this matters now" and the open risks; a participant card for each key attendee; the talking points and the questions to ask as two numbered columns; and the prep checklist with checkboxes.
- Refer to people by name and role only as the user gave them; keep the executive's private notes (watchouts, relationship angles) inside the page, since it is for the executive, and mark the page "Confidential — prepared for [executive]" at the top.
- List any context gaps from the brief in a small "Still to confirm" box at the foot.
- Give it clean, scannable styling and a "Print / Save as PDF" button.
- Present it as a rendered artifact when the surface supports it (Claude Cowork and the desktop app show it in the side panel). If artifacts aren't available, output the full HTML in one code block the user can save as
meeting-brief.htmland open.
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.
- 21d ago Changed · +13 lines 4e38a3d97bdf
- 22d ago First seen · 67 lines · 9 tokens per session scan A adbc52a1c15e
meeting-brief is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 3d ago), licensed MIT. It adds 9 tokens to every session and 712 once invoked, about $0.0000 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 2026-09-24.
Other commands, from other repositories
statusbar-preview
Render every style × theme combination using your real cached data.
session-log
Explain where session history lives now that the toolkit keeps no session log.
list-skills
Browse available skills by domain or list all skills with comprehensive categorization.
log-activity
Append a new entry to the activity log for this session.
sync
Manually sync current session to GitHub now.
process-inbox
Process the inbox. Read everything the user dropped in (notes, links, a deck, a messy folder) and route each fact to the most specific workspace file, separating facts from assumptions and open questions, without inventing anything.