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 lsegal/aviary --skill himalayagit clone --depth 1 https://github.com/lsegal/aviaryWrote 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/lsegal/aviary/himalaya)<a href="https://agentmods.dev/skills/lsegal/aviary/himalaya"><img src="https://agentmods.dev/badge/skills/lsegal/aviary/himalaya/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/skills/lsegal/aviary/himalaya"><img src="https://agentmods.dev/badge/skills/lsegal/aviary/himalaya.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 | $0.00057 | $0.00485 |
| Opus 5.5 | $0.00023 | $0.00194 |
| Sonnet 5.5 | $0.00011 | $0.00097 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
himalaya 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 2mo 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
Use this skill to perform email operations through the local himalaya binary.
Read-Only Commands
Inspect mailbox state before making changes:
himalaya account list— show configured accountshimalaya account doctor— diagnose account configurationhimalaya folder list— list mailbox foldershimalaya envelope list --folder INBOX— list messages in a folderhimalaya envelope list --folder INBOX --query "subject:invoice"— search by queryhimalaya envelope thread <envelope-id>— show a message threadhimalaya message read <envelope-id>— read a message bodyhimalaya message export <envelope-id>— export raw message (EML)
State-Changing Commands
Treat these as explicit user-requested actions:
- Flags:
himalaya flag add <id> seen,flag set,flag remove - Messages:
himalaya message copy <id> --to Archive,message move,message delete - Folders:
himalaya folder add <name>,folder delete,folder purge,folder expunge - Send:
himalaya message send --from personal --to [email protected] --subject "Re: meeting",template send,template save
Workflow
- List envelopes:
himalaya envelope list --folder INBOX - Read target message:
himalaya message read <envelope-id> - Act on it (flag, move, reply, delete) only when the user confirms
Confirm before destructive operations (delete, purge, expunge).
Rules
- Preserve envelope IDs, folder names, and account names exactly as returned
- Respect the configured
allowed_commandslist - Default to INBOX unless another folder is specified
- Use
--output jsonfor machine-readable output (appended automatically)
What ships with it
1 file 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.
- 2mo ago First seen · 44 lines · 57 tokens per session scan A 52f7aabe0c3e
himalaya is a skill published in the GitHub repository lsegal/aviary (12 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 485 once invoked, about $0.0002 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 skills, from other repositories
agent-user-tools
Agent skill for user-tools - invoke with $agent-user-tools.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
slack
Use the assigned Slack bot from Slack conversations, Paperclip tasks, and routines to read shared discussions and collaborate.
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
notion
Notion API for creating and managing pages, databases, and blocks.
himalaya
CLI to manage emails via IMAP/SMTP. Use himalaya to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).