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 cxcscmu/SkillLearnBench --skill email-schedulinggit clone --depth 1 https://github.com/cxcscmu/SkillLearnBenchWrote 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/cxcscmu/skilllearnbench/email-scheduling)<a href="https://agentmods.dev/skills/cxcscmu/skilllearnbench/email-scheduling"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/email-scheduling/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/cxcscmu/skilllearnbench/email-scheduling"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/email-scheduling.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 | $0.00022 | $0.00451 |
| Opus 5.5 | $0.00009 | $0.00180 |
| Sonnet 5.5 | $0.00004 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
email-scheduling 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 1mo 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.
What it actually says
Email-Based Meeting Scheduling
Workflow
1. Parse Email Requests
Extract from each email:
- Duration: e.g., "one-hour", "1.5 hour", "45-minute"
- Date constraint: e.g., "March 9th, 2026"
- Time window: e.g., "10:00am to 2:00pm", "1:00 PM and 5:00 PM PST"
- Sender email: from the
from_emailfield
2. Timezone Conversion
- If the request specifies a timezone different from the calendar, convert:
- PST to ET: add 3 hours (e.g., 1:00 PM PST = 4:00 PM ET)
- CST to ET: add 1 hour
- MST to ET: add 2 hours
3. Scheduling Strategy
- Find the earliest available slot that satisfies all constraints
- When multiple requests target the same day, schedule them so all can be accommodated
- Blue (low-priority) calendar blocks can be overwritten
- Never overlap with non-overwritable blocks
4. Reply Template Format
Hi,
Thank you for your meeting request.
I can be available:
Date: {day_name}, {month} {DD}, {YYYY}
Time: {HH:MM AM/PM} - {HH:MM AM/PM}
Duration: {meetingDuration} hour(s)
If this time doesn't work, please let me know your preferred alternatives.
Best regards,
ConSkillBench
5. Formatting Rules
- Date:
Monday, March 09, 2026(zero-padded day, full month name) - Time:
09:00 AM - 10:30 AM(zero-padded hours, AM/PM with space) - Duration: use "hour(s)" as unit; for 45 min use "0.75 hour(s)"
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.
- 1mo ago First seen · 51 lines · 22 tokens per session scan A d82a235a5b44
email-scheduling is a skill published in the GitHub repository cxcscmu/SkillLearnBench (91 stars, last pushed 21d ago), licensed MIT. It adds 22 tokens to every session and 451 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
scheduling-tasks
Advanced scheduling through the letta cron CLI for other conversations, computers, run history, and schedule replacement. Use Wake for ordinary create/list/cancel operations in the current conversation.
working-across-computers
Guides work across Cloud, local, and other available computers, including teleporting conversations, running remote subagents, and transferring files. Load when a request needs the user's laptop or another machine's files, apps, or tools; when connecting a computer; or when moving or delegating work between local and…
customizing-statusline
Creates, edits, and migrates Letta Code statusline mods. Use when handling the /statusline command or continuing work started by /statusline.
gmail-skill
Manage Gmail - send, read, search emails, manage labels and drafts. Use when user wants to interact with their Gmail account for email operations.
static
Stash is your personal home for agent work. Everything you create is scoped to your account — it is yours alone, with nothing to pick or set up first. Your Stash has three primary surfaces.
ceo-setup
One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.