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 InternLM/WildClawBench --skill calendar-remindersgit clone --depth 1 https://github.com/InternLM/WildClawBenchWrote 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/internlm/wildclawbench/calendar-reminders)<a href="https://agentmods.dev/skills/internlm/wildclawbench/calendar-reminders"><img src="https://agentmods.dev/badge/skills/internlm/wildclawbench/calendar-reminders.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 36 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00049 | $0.00568 |
| Opus 5 | $0.00024 | $0.00284 |
| Sonnet 5 | $0.00010 | $0.00114 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade B, and why
calendar-reminders scanned grade B with 2 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 8d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
The wrapper uses `--noauth_local_server` to print instructions. Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- The planner runs `gcalcli`/`khal` using `subprocess.check_output([...], shell=False)` (argument-list form; safe against shell injection from event titles). How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gcalcli calendar wrapper + reminder planner
This skill provides:
scripts/calendar— wrapper aroundgcalcliscripts/calendar_reminder_plan.py— produces a JSON plan for reminder schedulingreferences/openclaw-calendar.example.json— example config format
Config
Copy the example config to a private location and edit it:
- Default path:
~/.config/openclaw/calendar.json - Override with env:
OPENCLAW_CALENDAR_CONFIG=/path/to/calendar.json
Requirements
- Required:
python3,gcalcli - Optional (for CalDAV/iCloud):
vdirsyncer,khal
Security notes (why ClawHub may flag this)
This skill invokes external binaries and is config-driven.
- The planner runs
gcalcli/khalusingsubprocess.check_output([...], shell=False)(argument-list form; safe against shell injection from event titles). - If you wire a cron job to run
vdirsyncerSyncCommand, make sure you run it as an argv list (subprocess.run(cmd_list, shell=False)), not as a shell string. - Only point
gcalcliPath/khalBinto trusted binaries (prefer absolute paths). Don’t run untrusted paths.
Auth (Google)
gcalcli requires OAuth. On headless servers you may need SSH port-forwarding.
The wrapper uses --noauth_local_server to print instructions.
Reminder planning
The planner outputs a JSON blob describing reminders to schedule. A separate cron job (or an agent turn) can read it and create one-shot OpenClaw reminders.
Defaults:
- Ignore birthdays.
- Timed events are considered important.
- All-day events only trigger reminders if their title matches configured keywords.
Wiring a daily reminder scheduler (OpenClaw)
Create a daily cron job (e.g. 00:05 local time) that:
- If CalDAV is enabled in config, runs the configured
vdirsyncersync command. - Runs
scripts/calendar_reminder_plan.pyto get a JSON plan. - For each planned reminder, creates a one-shot OpenClaw
systemEventreminder atreminderAtUtc. - Writes a small state file so you don’t schedule duplicates.
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.
- 8d ago First seen · 58 lines · 0 tokens per session scan B 8580d9533af9
calendar-reminders is a skill published in the GitHub repository InternLM/WildClawBench (516 stars, last pushed 22d ago), licensed MIT. It adds 49 tokens to every session and 568 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (asks the agent to reveal its instructions, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
file-manager
A file and folder management helper for organizing files on a computer.
computer-use
Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…
meetings
Context for working with the Meetings app's data — where a meeting's notes, diagram, transcript-derived tasks, and calendar cache live, what the lifecycle states mean, and how the app's agents are driven. Load when the user asks about a meeting's notes or action items, or when writing/reading files under the meetings…
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
pto-planning
Check an employee's PTO balance and policy, then plan or submit a time-off request.
mochi-tips
Feature tips catalog for new users. Plan skill loads this to pick a tip during the first week.