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 commands/ashtonau/pear-plugin/schedulegit clone --depth 1 https://github.com/AshtonAU/pear-pluginWhat 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 | $0.00011 | $0.00174 |
| Opus 5 | $0.00005 | $0.00087 |
| Sonnet 5 | $0.00002 | $0.00035 |
| Haiku 4.5 | $0.00001 | $0.00017 |
Grade A, and why
schedule 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 2d 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
Help the user find optimal meeting times using pear_find_best_time.
- Parse the arguments for duration (default 30 minutes if not specified) and any description
- Use a search range of the next 5 business days unless the user specifies otherwise
- Call
pear_find_best_timewith appropriate preferences (default to work hours 9-17, weekdays) - Present the top 3-5 results with:
- Day and time
- Score and reasoning
- Any conflicts nearby
- Ask the user which slot they want, then offer to create the event with
pear_create_event
ARGUMENTS: $ARGUMENTS
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.
- 2d ago First seen · 19 lines · 0 tokens per session scan A 25e7dc69bca9
schedule is a command published in the GitHub repository AshtonAU/pear-plugin (6 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 174 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
check-tcc
Print che-ical-mcp's current TCC permission state, binary path, and ready-to-paste reset / re-prompt commands. Use when user says "check TCC", "permission status", "tccutil"。.
review
Stratified code review routed by risk tier (RFC 0013/0014) — not a flat scan.
quick-event
Quickly create a calendar event from natural language when the time and place are already known and stated directly. For deriving an event from a source — a meeting notice, an announcement, a message thread — where the time may have been corrected and the basis should be recorded, use the archive-event skill instead.
remind
Create a reminder from natural language.
week
Show this week's calendar overview.
today
Show today's calendar events and pending reminders.