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 zapier/wade-skills --skill meeting-follow-up-pipelinegit clone --depth 1 https://github.com/zapier/wade-skillsWrote 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/zapier/wade-skills/meeting-follow-up-pipeline)<a href="https://agentmods.dev/skills/zapier/wade-skills/meeting-follow-up-pipeline"><img src="https://agentmods.dev/badge/skills/zapier/wade-skills/meeting-follow-up-pipeline/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/zapier/wade-skills/meeting-follow-up-pipeline"><img src="https://agentmods.dev/badge/skills/zapier/wade-skills/meeting-follow-up-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
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 →
- medium Excessive Agency · line 101 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 173 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 174 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00061 | $0.01569 |
| Opus 5 | $0.00030 | $0.00785 |
| Sonnet 5 | $0.00012 | $0.00314 |
| Haiku 4.5 | $0.00006 | $0.00157 |
Grade A, and why
meeting-follow-up-pipeline 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Follow-Up Pipeline
Close the loop after a meeting. Turn a finished conversation into clarity and shipped follow-ups, so nothing important gets dropped.
The job in one line:
meeting happened → clarity shipped → nothing important gets dropped
This is not a transcript dump and not a generic recap.
Setup
Fill in the tools you use (or let the agent ask). The skill degrades gracefully — if a source isn't available, it flags that and asks for pasted input instead.
[MEETING NOTES TOOL]— where your notes/transcript live (Granola, Fathom, Otter, Fireflies, Fellow, or pasted text)[EMAIL]— your email, for drafting external follow-ups[CHAT]— your team chat, for drafting internal follow-ups (Slack, Teams, etc.)[TASK SYSTEM]— where action items get promoted (Coda, Notion, Asana, Linear, a spreadsheet)[DRAFTS AREA]— where sendable drafts get staged for review before sending (a drafts folder, an "outbox" doc, etc.)
When to Use
- "Run the meeting follow-up pipeline"
- "Debrief my last meeting"
- "Process this meeting"
- "What are the key follow-ups from that meeting?"
Right after a meeting, during an end-of-day wrap to catch missed follow-ups, or before the next meeting in a chain to avoid dropping context.
Scope Rule: All Meetings Eligible, Not All Get the Same Treatment
Classify the meeting and route it to one of three levels. Run the workflow for all three — just don't force heavy outputs when the meeting doesn't justify them.
Level 1 — Full pipeline: external, customer/prospect, partner, candidate interviews, board/investor, high-stakes internal decision meetings.
Level 2 — Internal substantive: leadership reviews, initiative reviews, staffing/org discussions, important cross-functional working sessions.
Level 3 — Lightweight capture: routine status meetings, normal recurring syncs, low-novelty internal meetings.
Default Target
If the user only says "run the pipeline" / "process this meeting" / "debrief my last meeting":
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 · 187 lines · 61 tokens per session scan A df11706095f8
meeting-follow-up-pipeline is a skill published in the GitHub repository zapier/wade-skills (87 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 1,569 once invoked, about $0.0003 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
hourly-rate-time
A time-management method based on assigning a high personal value to each hour. It treats time as a limited resource and uses that value to decide which tasks to do, outsource, or skip.
screen-detox
A habit-change framework for reducing non-work screen use such as social media, short videos, games, and endless scrolling.
monkey-mind-meditation
A meditation and reflection guide for a busy or anxious mind. It treats recurring thoughts as something to observe and examine, while noting that acute serious mental-health problems need professional care.
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
building-team-culture
Build or refresh a team culture code, norms, and reinforcement plan.
energy-management
Build an Energy Management System: drivers/drains map, energy-aligned schedule, recovery routines.