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/foneclaw-ai/foneclaw-android/mailnpx skills add FoneClaw-AI/foneclaw-android --skill mailgit clone --depth 1 https://github.com/FoneClaw-AI/foneclaw-androidWrote 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/foneclaw-ai/foneclaw-android/mail)<a href="https://agentmods.dev/skills/foneclaw-ai/foneclaw-android/mail"><img src="https://agentmods.dev/badge/skills/foneclaw-ai/foneclaw-android/mail.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 | $0.00017 | $0.00547 |
| Opus 5 | $0.00009 | $0.00273 |
| Sonnet 5 | $0.00003 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
mail 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mail Skill
Use this skill when the user asks to search, read, summarize, send, reply to, forward, or delete email.
Tools
mail_account_list: list accounts, or match by exact account ID, exact full email address, exact alias, then fuzzy alias/email.mail_list: list, filter, and search summaries. Itsquerysearches subject, sender, recipients, and body. Use its opaquemessageReffor later operations.mail_read: read onemessageRef, return attachment metadata and paged body content, and mark the server message as read.mail_send: sendNEW,REPLY,REPLY_ALL, orFORWARDmail, optionally with files the user selected in the current message.mail_delete: move up to 20messageRefvalues to Trash, or permanently delete only when the user explicitly requests permanent deletion.
Rules
- Never ask the user to provide a mail password inside a tool call.
- Mail account credentials are configured externally through MailAccountConfig.
- Leave
accountIdempty only when one account exists or exactly one account is the default. If the tool returnsaccount_selection_required, callmail_account_listand ask the user to choose; never select the first account. - Prefer
mail_listbeforemail_read,mail_sendreply modes, ormail_delete. - After every successful or partial
mail_read, summarize the message in the same response. Continue withnextBodyCursoronly when the remaining body is needed. mail_sendandmail_deleterequire approval. Do not claim an email was sent or deleted before the tool result confirms it.- An
unknownsend/delete result must not be retried automatically. - Empty subjects are allowed; an empty send body is not.
- Attachments must use the exact
attachmentRef, file name, MIME type, and size announced for the current user message. Maximum: 10 files, 10 MiB each, 18 MiB total. Do not invent a local path, content URI, URL, or attachment reference. - Reply and forward do not automatically include attachments from the source message.
TRASHmust not fall back to permanent deletion when no reliable Trash folder exists.- Keep summaries concise and mention important attachment metadata.
- Do not expose authentication details in responses.
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 · 46 lines · 17 tokens per session scan A e2c0a183d3b7
mail is a skill published in the GitHub repository FoneClaw-AI/foneclaw-android (5 stars, last pushed 3d ago), licensed MIT. It adds 17 tokens to every session and 547 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 skills, from other repositories
alarm
Call the unintent tool with the following exact parameters.
calendar
Call the unintent tool with the following exact parameters.
timer
Call the unintent tool with the following exact parameters.
read_calendar
Read upcoming calendar events.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…