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.
git clone --depth 1 https://github.com/AshtonAU/pear-pluginWrote 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/commands/ashtonau/pear-plugin/pear-setup)<a href="https://agentmods.dev/commands/ashtonau/pear-plugin/pear-setup"><img src="https://agentmods.dev/badge/commands/ashtonau/pear-plugin/pear-setup/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/commands/ashtonau/pear-plugin/pear-setup"><img src="https://agentmods.dev/badge/commands/ashtonau/pear-plugin/pear-setup.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 | $0.00014 | $0.00410 |
| Opus 5.5 | $0.00006 | $0.00164 |
| Sonnet 5.5 | $0.00003 | $0.00082 |
| Haiku 4.5 | $0.00001 | $0.00041 |
Grade A, and why
pear-setup 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 11d 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 verify their Pear setup by testing the connection:
First inspect the tools exposed by the connected client; do not assume a fixed count or that unavailable tools can be called.
-
If available, call
pear_list_calendarsto test Calendar access- On success: Show the list of calendars and confirm only "Pear can read your connected iCloud calendars". A Calendar check does not verify Contacts, Mail, or Reminders access. Explain that Apple Reminders support is limited to legacy CalDAV data; upgraded Reminders are not accessible
- On auth error (-32001): The API key is missing or invalid. Tell the user:
- Set the environment variable:
export PEAR_API_KEY=pear_sk_... - Sign up at pearmcp.com to get an API key
- They need an Apple app-specific password connected to their Pear account
- Set the environment variable:
- On connection error: The MCP endpoint may be unreachable. Suggest checking
PEAR_MCP_URLor network connectivity
-
If the user expects Mail support, call
pear_list_mail_folders- On success: Confirm Mail is connected too
- On failure while calendars succeeded: Explain that Calendar was verified, but Mail was not. Mail may require the mailbox's real
@icloud.comaddress or iCloud Mail custom-domain address during Pear onboarding
-
On success, summarize what's available:
- Number of calendars found (list their names)
- Mail status if checked
- Available commands:
/pear:briefing,/pear:schedule - Mention they can ask things like "What's on my calendar today?" or, if Mail was verified, "Show me unread iCloud Mail from today"
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.
- 11d ago Changed · +2 lines abc7255bf5aa
- 1mo ago First seen · 25 lines · 14 tokens per session scan A e8aba17e1bfb
pear-setup is a command published in the GitHub repository AshtonAU/pear-plugin (7 stars, last pushed 9d ago), licensed MIT. It adds 14 tokens to every session and 410 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
firebase-publish
Create or reuse a Firebase project, configure Hosting, and deploy the current static site. Never deletes.
p3-ux-wireframes
Creates wireframes (ASCII art) for the most important screens with interaction descriptions.
dare-llm-integration
Integração segura e eficiente com LLMs (Gemini, Claude, OpenAI, Ollama) em projetos DARE.
note
Zero-friction idea capture. Append, list, or promote notes to todos.
onboard
/anty:onboard — QUEST-Based Conversational Interview.
checklist
Generate a custom checklist for the current feature based on user requirements.