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 agentmods add skills/craftos-dev/craftbot/gcalcli-calendarnpx skills add CraftOS-dev/CraftBot --skill gcalcli-calendargit clone --depth 1 https://github.com/CraftOS-dev/CraftBotWrote 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/craftos-dev/craftbot/gcalcli-calendar)<a href="https://agentmods.dev/skills/craftos-dev/craftbot/gcalcli-calendar"><img src="https://agentmods.dev/badge/skills/craftos-dev/craftbot/gcalcli-calendar.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.02106 |
| Opus 5 | $0.00021 | $0.01053 |
| Sonnet 5 | $0.00008 | $0.00421 |
| Haiku 4.5 | $0.00004 | $0.00211 |
Grade A, and why
gcalcli-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 4d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gcalcli-calendar
Use gcalcli to read/search/manage Google Calendar with minimal tool calls and minimal output.
Rules
CLI flag placement (critical)
- Global flags (
--nocolor,--calendar) go BEFORE the subcommand. - Subcommand-specific flags go AFTER the subcommand name.
- Example:
gcalcli --nocolor delete --iamaexpert "query" start end— NOTgcalcli --nocolor --iamaexpert delete .... - This applies to ALL subcommand flags:
--iamaexpert(delete),--noprompt/--allday(add),--use-legacy-import(import), etc.
Output & language
- Don't print CLI commands/flags/tool details unless the user explicitly asks (e.g. "show commands used", "/debug", "/commands").
- If asked for commands: print ALL executed commands in order (including retries) and nothing else.
- Don't mix languages within one reply.
- Be concise. No scope unless nothing found.
Dates & formatting
- Human-friendly dates by default. ISO only if explicitly requested.
- Don't quote event titles unless needed to disambiguate.
Calendar scope
- Trust gcalcli config (default/ignore calendars). Don't broaden scope unless user asks "across all calendars" or results are clearly wrong.
Agenda (today-only by default)
- If user asks "agenda" without a period, return today only.
- Expand only if explicitly asked (tomorrow / next N days / date range).
Weekday requests (no mental math)
If user says "on Monday/Tuesday/..." without a date:
- fetch next 14 days agenda once,
- pick matching day/event from tool output,
- proceed (or disambiguate if multiple).
Finding events: prefer deterministic agenda scan (meaning-first)
When locating events to cancel/delete/edit:
- Prefer
agendaoversearch. - Use a bounded window and match events by meaning (semantic match) rather than exact text.
- Default locate windows:
- If user gives an exact date: scan that day only.
- If user gives a weekday: scan next 14 days.
- If user gives only meaning words ("train", "lecture", etc.) with no date: scan next 30 days first.
- If still not found: expand to 180 days and say so only if still empty.
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.
- 4d ago First seen · 164 lines · 42 tokens per session scan A 3bd3cee25ac3
gcalcli-calendar is a skill published in the GitHub repository CraftOS-dev/CraftBot (376 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 2,106 once invoked, about $0.0002 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
artifact-storage-policy
管理 Codex 交付物的專案識別、Google Drive／GitHub 路由、檔名、儲存位置與回讀驗證；凡工作報告、外部保存、交付成果或新 repository 選擇涉及遠端儲存時使用。.
output-contract
任務完成前需要一致交付格式、修改清單、測試結果、待確認事項、或使用者明確要求「完成後列出」時使用。適用於程式碼、設定、文件、skills、同步與多步驟任務收尾；本 Skill 不取代內容 readiness 或風險檢查。.
save-to-notion
將 Codex 對話、回答、決策、工作流程與可重用知識整理到使用者的 Notion 知識 Hub。當使用者明確說「save to notion」，或要求保存、歸檔、整理、分類、版本化、更新到 Notion 時使用；若只是要求產出一般報告或文件，除非另有指定，不要觸發 Notion 實際寫入。.
delivery-manifest
每次產生、修改、上傳或寄送檔案後，產生統一的交付物索引 (Delivery Manifest)，並嚴格控管 Google Drive 上傳路徑。.
intent-to-mission-blueprint
Convert human operational intent into a Tandem mission blueprint with phased workstreams, explicit handoffs, reusable outputs, and recurrence-aware setup.
marketing-brand-voice
Legacy fallback for brand governance and style policy work. Prefer copywriting and copy-editing for operational production tasks. Use when documenting or auditing voice rules, not as the default drafting workflow.