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 sandbaseai/sandbase-skills --skill meeting-minutesgit clone --depth 1 https://github.com/sandbaseai/sandbase-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/sandbaseai/sandbase-skills/meeting-minutes)<a href="https://agentmods.dev/skills/sandbaseai/sandbase-skills/meeting-minutes"><img src="https://agentmods.dev/badge/skills/sandbaseai/sandbase-skills/meeting-minutes/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/sandbaseai/sandbase-skills/meeting-minutes"><img src="https://agentmods.dev/badge/skills/sandbaseai/sandbase-skills/meeting-minutes.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 | $0.00036 | $0.01906 |
| Opus 5 | $0.00018 | $0.00953 |
| Sonnet 5 | $0.00007 | $0.00381 |
| Haiku 4.5 | $0.00004 | $0.00191 |
Grade A, and why
meeting-minutes 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 8d 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.
This is a copy
94% identical to meeting-minutes — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Minutes Skill — Short Internal Meetings
Purpose / Overview
This Skill produces high-quality, consistent meeting minutes for internal meetings that are 60 minutes or shorter. Output is designed to be clear, actionable, and easy to convert into task trackers (e.g., GitHub Issues, Jira). The generated minutes prioritize decisions and action items so teams can move quickly from discussion to execution.
When source material is supplied as a web page or a published video, read the SandBase API map. Resolve the current schema with sandbase_describe_tool before using a listed capability through sandbase_call_tool.
When to Use
Use this skill when:
- Internal syncs, standups, design reviews, triage, planning or ad-hoc meetings with short duration
- Situations that require a concise record of decisions, assigned action items, and follow-ups
- Creating a standardized minutes document from a live meeting, transcript, recording, or notes
Operational Workflow
Phase 1: Intake (before drafting)
- Obtain meeting metadata: title, date, start/end time (or duration), organizer, and intended audience.
- Confirm available inputs: agenda, slides, recording, transcript, or raw notes.
- If key details are missing, ask up to 3 clarifying questions before producing minutes (see "Discovery" below).
Phase 2: Capture (during / immediately after meeting)
- Record attendees and absentees.
- Capture brief notes per agenda item with time markers if available.
- Record explicit decisions, rationale summary (1–2 sentences), and action items (owner + due date).
Phase 3: Drafting
- Generate minutes following the Strict Minutes Schema (below).
- Ensure every action item includes owner, due date (or timeframe), and acceptance criteria when applicable.
- Mark unresolved issues or items requiring follow-up in the Parking Lot.
Phase 4: Review & Publish
- If explicitly requested and authorized, send the draft to the meeting organizer or a designated reviewer for quick verification (within 24 hours).
- Publish final minutes to the agreed channel or create tasks in the team's tracker only when the user explicitly requests and authorizes those external actions.
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.
- 8d ago First seen · 238 lines · 36 tokens per session scan A d547b938b3d8
meeting-minutes is a skill published in the GitHub repository sandbaseai/sandbase-skills (159 stars, last pushed 4d ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,906 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to meeting-minutes, differing in 8 lines, and is treated as a copy.
Other skills, from other repositories
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…
grill-me
Grill the user about a requirement, decision, or idea before implementation, then produce an actionable planning report without writing code. Use when the user wants to clarify requirements, stress-test an idea, compare approaches, or plan before coding.
triage
Label-based issue triage workflow. Use when a batch of issues needs sorting by priority/type, or the task mentions "triage", "分流", "prioritize issues", "label". Pulls issues, classifies them, and applies labels/assignees via gh.
yao-board
Kanban board and task query expert. ALWAYS invoke this skill when the user asks about boards, tasks, task status, or project progress. Do not guess task state — use this skill first.
github
GitHub operations via gh CLI or Python API. Use when: listing repos, creating/viewing issues and PRs, checking CI runs, managing releases, or querying the GitHub API. NOT for: general git commands (use git directly), cloning private repos without auth.
dsh-skill-dev
A specialist review agent for software that handles purchasing, suppliers, payments, or spending approvals.