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 opendatahub-io/ai-helpers --skill email-meeting-summarygit clone --depth 1 https://github.com/opendatahub-io/ai-helpersWrote 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/opendatahub-io/ai-helpers/email-meeting-summary)<a href="https://agentmods.dev/skills/opendatahub-io/ai-helpers/email-meeting-summary"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/email-meeting-summary/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/opendatahub-io/ai-helpers/email-meeting-summary"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/email-meeting-summary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00078 | $0.01691 |
| Opus 5 | $0.00039 | $0.00846 |
| Sonnet 5 | $0.00016 | $0.00338 |
| Haiku 4.5 | $0.00008 | $0.00169 |
Grade A, and why
email-meeting-summary scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Email Meeting Summary
Read a Google Meet transcript, identify discussion topics, summarize decisions and action items for the chosen topic, and compose a Gmail draft for review.
Prerequisites
gwsbinary must be on$PATH- Authenticated: run
gws auth loginif not already logged in. The--readonlyflag is sufficient for reading calendar/docs/drive, but draft creation requires thegmail.composescope which is included in the default (non-readonly) login.
If gws is not installed or authentication fails, tell the user to follow the
setup instructions in the google-workspace skill.
Helper scripts are located in ${CLAUDE_SKILL_DIR} and require Python 3.10+.
Step 1: Identify the Meeting
Run the search once and save the result to a temp file:
EVENT_FILE=$(mktemp /tmp/meeting_event.XXXXXX)
# With a keyword (argument provided):
python3 "${CLAUDE_SKILL_DIR}/scripts/find_meeting.py" --days 7 "<keyword>" > "$EVENT_FILE"
# With keyword + specific date (recurring meeting):
python3 "${CLAUDE_SKILL_DIR}/scripts/find_meeting.py" --days 7 --date "<YYYY-MM-DD>" "<keyword>" > "$EVENT_FILE"
# No argument — list all recent events:
python3 "${CLAUDE_SKILL_DIR}/scripts/find_meeting.py" --days 7 > "$EVENT_FILE"
The script always outputs JSON. Read EVENT_FILE and display the result(s) to
the user as a human-readable list.
The script searches the past 7 days (up to now). When a keyword matches
multiple occurrences of a recurring meeting, it automatically picks the best
one: the occurrence on --date if given, otherwise today's, otherwise the most
recent past one.
Always confirm with the user before proceeding, regardless of how many
results were found. Use AskUserQuestion:
"I found: on at . Is this the meeting you want to summarize? (yes / no — if no, describe the meeting you meant)"
If the user says no, ask for clarification and re-run find_meeting.py with a
corrected keyword or --date, overwriting EVENT_FILE. If multiple events were
returned, list them and ask the user to pick one by number, then re-run with
--date to narrow to that occurrence.
What ships with it
3 files 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.
- 12d ago First seen · 192 lines · 78 tokens per session scan A 378e463f6e7a
email-meeting-summary is a skill published in the GitHub repository opendatahub-io/ai-helpers (37 stars, last pushed 5d ago), licensed Apache-2.0. It adds 78 tokens to every session and 1,691 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 2026-08-30.
Other skills, from other repositories
quick-tasks
Token-saving mode for everyday lightweight work. Use for one-line fixes, typo/config-value changes, quick questions ("what does this function do?"), throwaway scripts, and anything that ends inside a single file. Output is a minimal diff and a short report. For multi-file, design, or new-feature work, switch to the…
Dispatching Parallel Agents
Concurrent execution of independent subtasks using multi-agent scheduling.
Executing Implementation Plans
Systematic execution of multi-step implementation plans with milestone verification.
selection-processor
Use when processing only a selected portion of text rather than a full file, to save tokens and enable targeted AI operations.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
nft-standards
Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.