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 swan-gtm/gtm-skills --skill conference-shared-calendargit clone --depth 1 https://github.com/swan-gtm/gtm-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/swan-gtm/gtm-skills/conference-shared-calendar)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/conference-shared-calendar"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/conference-shared-calendar/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/swan-gtm/gtm-skills/conference-shared-calendar"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/conference-shared-calendar.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 | $0.00052 | $0.00768 |
| Opus 5.5 | $0.00021 | $0.00307 |
| Sonnet 5.5 | $0.00010 | $0.00154 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
conference-shared-calendar 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 23d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shared conference calendar
Create a useful reference agenda that does not consume people's meeting availability.
Establish the inputs
Use assets/calendar-worksheet.md. Reuse information already supplied. Ask only for missing facts that affect correctness: official source, event dates, venue IANA timezone, calendar owner/destination, and intended readers/editors. Never infer timezone from the operator's computer. Distinguish a private team calendar from a publicly shared event calendar.
Inspect the existing destination and prior imports before creating anything. Prefer an authorized existing calendar when it serves the purpose. Use a connector/API when available; otherwise use the authenticated browser. With no live access, prepare an ICS and exact setup instructions and label the live setup unfinished.
Normalize the agenda
Read the official agenda and linked session details. Capture source ID, title, date, start/end, timezone, venue/room, speaker, source URL, and confidence. Retain concurrent sessions; this is a reference calendar, not one person's itinerary. Do not copy private notes into shared descriptions.
Prefer explicit organizer updates over stale listings. Keep a source/change log and flag contradictions. Never turn an unpublished time into a precise appointment: a known date may have a Free all-day “TIME TBD” marker; unknown dates stay in a separate unresolved list. Do not confuse a short public workshop with an independently arranged longer activity.
Build and publish
- Create a separately named reference calendar with the venue timezone. Verify the destination before importing or writing.
- Make reference events Free / transparent. Colors are cosmetic. Sharing “see only free/busy” is a visibility permission and is different from event Free/Busy status.
- Include source links and useful logistics. A reference copy of a dinner does not accept the original invitation or add guests. Do not add ATTENDEE fields to an ICS reference export.
- Prefer API upserts with a saved source-ID → remote-event-ID mapping for ongoing maintenance. If using ICS, assign stable UIDs from conference namespace plus source ID; use valid timezone-aware times, CRLF, escaped text, UTF-8-safe 75-octet line folding, and exclusive all-day end dates. Validate event counts, ordering, and sample times before import.
- ICS import is a snapshot. Stable UIDs alone do not guarantee that repeated Google imports update existing entries. Do not reimport blindly. Inspect and update the existing records, or prepare a deliberate replacement plan without deleting unrelated events.
- Apply the requested sharing permissions. Give viewers event details and editors only the intended editing rights. Public access is a separate explicit choice. If sharing would notify people and the user has not authorized invitations, finish the calendar and present the exact recipients/permissions for approval.
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.
- 23d ago First seen · 40 lines · 52 tokens per session scan A 5026790ebacb
conference-shared-calendar is a skill published in the GitHub repository swan-gtm/gtm-skills (181 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 768 once invoked, about $0.0002 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 2026-09-24.
Other skills, from other repositories
edgeos
Talk to the EdgeOS popup-village platform — read the event schedule in the village's local time, RSVP (after asking the person), list venues and who is going to an event, search the attendee directory and read the person's own Edge City profile through the Agent Village control plane (two scripts; the app reads EdgeOS…
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.