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 skills add TheCraigHewitt/cowork-starter-pack --skill meeting-debriefgit clone --depth 1 https://github.com/TheCraigHewitt/cowork-starter-packWrote 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/thecraighewitt/cowork-starter-pack/meeting-debrief)<a href="https://agentmods.dev/skills/thecraighewitt/cowork-starter-pack/meeting-debrief"><img src="https://agentmods.dev/badge/skills/thecraighewitt/cowork-starter-pack/meeting-debrief/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/thecraighewitt/cowork-starter-pack/meeting-debrief"><img src="https://agentmods.dev/badge/skills/thecraighewitt/cowork-starter-pack/meeting-debrief.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 | $0.00081 | $0.01259 |
| Opus 5 | $0.00041 | $0.00629 |
| Sonnet 5 | $0.00016 | $0.00252 |
| Haiku 4.5 | $0.00008 | $0.00126 |
Grade A, and why
meeting-debrief 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 12d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Debrief
The meeting just ended. The user has rough notes or a memory. Turn that into action items, a follow-up email, and a durable record — in under three minutes.
Before starting
- Read
context/about-me.mdandcontext/voice.md— the follow-up email needs to sound like the user - Read
context/preferences.md— how they want action items formatted, sign-off preferences - Ask the user to either paste their notes or describe what happened. Don't guess.
- If there's a corresponding
meeting-prep-*.mdfile for this meeting, read it. Compare: what did you predict vs. what happened?
What to produce
Two outputs:
1. A debrief file saved to /output/meeting-debrief-{YYYY-MM-DD}-{attendee-or-topic}.md with five sections:
- What happened — 3–6 bullets summarizing the conversation. Factual.
- Decisions made — list them cleanly. One line each. (Feed these to the decision log over time.)
- Action items — for each: owner, what, deadline. Separate items owned by the user from items owned by others.
- Open questions — things that didn't get answered or got deferred.
- What to do next — the user's next move, specific.
2. A follow-up email draft — attached inline at the bottom of the debrief file under the heading ## Draft follow-up email. Under 150 words unless the situation genuinely requires more. Matches the user's voice. Confirms action items with clear deadlines. Ends with a specific next step.
Inputs
- The user's raw notes or verbal recap (required)
- The
meeting-prep-*.mdfile for this meeting, if it exists - Any relevant context from the project folder
How it works
- Parse the user's notes — separate facts from opinions from decisions
- If a meeting-prep file exists, reference it: did the attendee bring up what you expected? Were there surprises?
- Draft the five sections of the debrief
- Draft the follow-up email in the user's voice (see
voice.md). Keep it tight. - Save everything to the debrief file
- Tell the user: "Debrief saved. Follow-up email is ready to review at the bottom — say the word and I'll send it." (Do not send without approval. See global instructions.)
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.
- 12d ago First seen · 112 lines · 81 tokens per session scan A 01a0fd7bbc67
meeting-debrief is a skill published in the GitHub repository TheCraigHewitt/cowork-starter-pack (5 stars, last pushed 4mo ago), licensed MIT. It adds 81 tokens to every session and 1,259 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
give-me-tips
Explains any senpi tip in depth, including Tip: lines in the TUI. Use when the user asks about a tip, what a tipped feature does, or which tips they can see.
suede-onboarding
Suede-affiliated onboarding and activation strategy for first-run sequencing, empty states, setup checklists, activation milestones, time to value, and retention-linked measurement. Use when users sign up but fail to reach first value or the product needs a new first-session flow. NOT FOR: registration optimization…
google-apps-script
Build Google Apps Script automation for Sheets and Workspace. Custom menus, triggers (onEdit / time-driven / form submit), dialogs, sidebars, email batches, PDF export, external API. Use whenever the user wants to automate a Google Sheet, build a Sheets menu / sidebar / dialog, hit a Sheets row from email or a…
google-chat-messages
Send Google Chat messages via incoming webhooks — text, rich cards (cardsV2), threaded replies. TypeScript types, card builder utility, widget reference inline. Use whenever the user wants to post to Google Chat from a script, build a chatbot reply, send a notification card, build a Google Chat webhook integration, or…
parcel-tracking
Track parcels and check delivery status for Australian and international couriers. Searches Gmail for dispatch/shipping emails and provides tracking links for all major Australian couriers including AusPost, StarTrack, Aramex, CouriersPlease, Sendle, Toll, Team Global Express, DHL, FedEx, TNT, Hunter Express, Border…
skill-composer-studio
CHAIN multiple existing skills into custom multi-step workflows. Programmable skill combinations with automatic handoffs. Create composite skills from building blocks with conditional logic.