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 damianvtran/local-operator --skill schedulinggit clone --depth 1 https://github.com/damianvtran/local-operatorWrote 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/damianvtran/local-operator/scheduling)<a href="https://agentmods.dev/skills/damianvtran/local-operator/scheduling"><img src="https://agentmods.dev/badge/skills/damianvtran/local-operator/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/damianvtran/local-operator/scheduling"><img src="https://agentmods.dev/badge/skills/damianvtran/local-operator/scheduling.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 | $0.00044 | $0.00622 |
| Opus 5.5 | $0.00018 | $0.00249 |
| Sonnet 5.5 | $0.00009 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
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 5d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scheduling
Times for other people: zones named exactly, ambiguity engineered out, confirmations in the frame the attendee reads.
Zones
- Use IANA zone names (America/New_York, Europe/Berlin, Asia/Kolkata), never abbreviations. "ET" is ambiguous, "CST" means several different zones, "IST" at least three.
- Keep the zone ID attached to the time; a bare "14:00" is not schedulable.
- When converting, show the basis: "14:00 UTC = 10:00 New York (EDT)".
DST edges
- Transitions move a zone by an hour. Check the UTC offset for the DATE in question, not for today.
- Fall-back repeats an hour: 01:30 can occur twice. If a proposed time lands there, name the offset (01:30 EDT versus EST).
- Spring-forward skips an hour: a time in the gap does not exist. Never propose one.
- Recurring meetings: keep recurrences zoned (with the zone ID), so they stay at the local wall time. A fixed-UTC recurrence drifts an hour twice a year.
Restate in the recipient's zone
- Every proposal and confirmation gives the time in the OTHER person's zone, plus yours, plus the zone IDs: "10:00-10:30 Europe/London (11:00 for you, Europe/Berlin)".
- Avoid relative-only phrasing: "3pm my time" makes the reader do the conversion, and they will get it wrong when tired.
Working hours and buffers
- Judge the time against the recipient's working hours and week boundaries, not yours. A slot outside their 9-18 needs a stated reason.
- Leave buffers where the recipients' culture expects them; back-to-back chains across zones are a smell.
- Respect stated focus blocks and known out-of-hours patterns.
Confirm, then book
- A proposed slot is not a booking. Restate date, time, zone, and duration; get explicit confirmation before creating the invitation.
- The confirmation restates all four fields. Typos and DST errors are caught here or not at all.
- Change any field and it is a new proposal: reconfirm the whole thing.
Calendar etiquette
- No surprise short-notice meetings where avoidable; mark urgency only when it is real.
- Public holidays differ by country and region; check the attendee's region, not the country's default.
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.
- 5d ago First seen · 52 lines · 44 tokens per session scan A af25d65cd21f
scheduling is a skill published in the GitHub repository damianvtran/local-operator (218 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 622 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 2026-10-11.
Other skills, from other repositories
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
neosh
Run and manage long-lived coding agents in a neosh workspace from the command line — start conversations in any directory or git worktree, fan work out across many at once, watch and steer them while they run, read what they produced, and clean up. Use whenever the user asks to delegate work to neosh, run something…
google-workspace
Gmail, Calendar, Drive, Contacts, Sheets, and Docs integration via Python. Uses OAuth2 with automatic token refresh. No external binaries needed — runs entirely with Google's Python client libraries in the Hermes venv.
himalaya
CLI to manage emails via IMAP/SMTP. Use himalaya to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
notion
Notion API for creating and managing pages, databases, and blocks via curl. Search, create, update, and query Notion workspaces directly from the terminal.