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 tahirraufkeeyu/software-development-agent-stack--sdas --skill meeting-notesgit clone --depth 1 https://github.com/tahirraufkeeyu/software-development-agent-stack--sdasWrote 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/tahirraufkeeyu/software-development-agent-stack--sdas/meeting-notes)<a href="https://agentmods.dev/skills/tahirraufkeeyu/software-development-agent-stack--sdas/meeting-notes"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/meeting-notes/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/tahirraufkeeyu/software-development-agent-stack--sdas/meeting-notes"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/meeting-notes.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 | $0.00058 | $0.01942 |
| Opus 5 | $0.00029 | $0.00971 |
| Sonnet 5 | $0.00012 | $0.00388 |
| Haiku 4.5 | $0.00006 | $0.00194 |
Grade A, and why
meeting-notes 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 9d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
Trigger this skill when:
- A meeting has ended and someone needs to distribute notes to attendees and non-attendees.
- A transcript exists (from Otter, Granola, Fireflies, Zoom AI, Google Meet, or a scribe) and you need to distill it.
- A recurring meeting (staff, 1:1, design review) needs notes captured in a consistent format.
Do not use this skill for:
- Legal-grade records where verbatim matters (depositions, disputes) — use the raw transcript.
- Interview notes where the content is the notes (qualitative research) — use a research-specific template.
- Notes from a meeting you did not have a transcript for — ask the user for their rough notes first.
Inputs
Required:
- Transcript (pasted, file path, or link to Otter/Granola).
- Meeting name and date (UTC).
Optional:
- Attendees list (names and roles). If not provided, the skill will extract speakers from the transcript and ask about roles.
- Agenda (if one was circulated).
- Prior meeting notes (for recurring meetings — helps track follow-through on previous action items).
Outputs
A Markdown document following the structure in references/meeting-template.md:
- Meeting name and Date (UTC)
- Attendees (with roles)
- Agenda (if provided)
- Decisions — explicit yes/no decisions only
- Action Items — each with owner (named person) and due date
- Open Questions — things raised but not resolved
- Discussion Notes — bullet summary, not verbatim
- Next Meeting — date and agenda items carried forward
Tool dependencies
- Read — to load transcript files.
- Google Calendar MCP (optional) — to resolve attendee list and meeting time from the calendar invite.
- Notion MCP (optional) — to write the notes into a meetings database and link to prior meetings.
- Slack MCP (optional) — to post the notes summary into the team channel.
Procedure
- Parse the transcript. Identify speaker turns. If the transcript is from Otter/Granola, these are typically tagged; if raw, infer from context or ask.
- Resolve attendees. If not provided, list every distinct speaker. Match to the calendar invite if available. Tag each with their role.
- Identify decisions. A decision is an explicit yes/no or pick-A-or-B moment. Look for:
- "Let's go with X."
- "Decided: we will..."
- "Agreed, X by Y."
- The end of a debate where one option is adopted. A comment like "maybe we should..." is NOT a decision — it is a possible action item or an open question.
- Extract action items. An action item must name a person and a date.
- "Alice will send the doc" → action item if a date can be inferred ("by end of week"), otherwise move to Open Questions with a note to confirm owner+date.
- "Someone should look at this" → NOT an action item. Flag as Open Question.
- Implicit due dates ("before next meeting," "this week") should be resolved to a concrete date based on the meeting date.
- Identify open questions. Things that were raised, discussed inconclusively, and not converted into a decision or action item. Each should be one sentence, phrased as a question.
- Summarize discussion. For each agenda item (or each major topic if no agenda), write 2–5 bullets. Each bullet is a point made, not a line spoken. Combine repeated points. Omit:
- Greetings, goodbyes, small talk.
- Technical hiccups ("can you hear me?").
- Off-topic tangents unless they led to a decision or action item.
- Check follow-through. If prior meeting notes were provided, list which of the previous action items shipped, slipped, or are still in progress.
- Identify next meeting. Date, owner, and any agenda items explicitly carried forward.
- Draft the notes. Enforce the structure. Keep it scannable.
- Return for human review. Recommend sharing with attendees for corrections before publishing.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 151 lines · 58 tokens per session scan A 2c983c6f2c25
meeting-notes is a skill published in the GitHub repository tahirraufkeeyu/software-development-agent-stack--sdas (18 stars, last pushed 4mo ago), licensed MIT. It adds 58 tokens to every session and 1,942 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…