himalaya

himalaya is a skill for Claude Code, Codex from moltis-org/moltis. It costs 39 tokens per session (1,116 once invoked), scanned A, original, MIT.

A command-line email client for reading, organizing, composing, and sending email through services such as Gmail, IMAP, JMAP, Microsoft Graph, or local mail folders.

In plain words
What is it for?
Use it to list mail, inspect messages, manage accounts, compose email, and send messages from the command line.
Why use it?
It lets developers manage email from a terminal and work with several mail systems through one tool. The instructions specifically apply to version 2 of Himalaya.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for hermes-agent. Also seen: built for hermes-agent.

Good fit Use it to list mail, inspect messages, manage accounts, compose email, and send messages from the command line.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/moltis-org/moltis/himalaya
About the project

Moltis is a persistent personal agent server written in Rust that runs on hardware controlled by its user. It provides an AI agent with sandboxed command execution, model-provider connections, memory, voice, scheduling, messaging integrations, browser automation, and MCP tools. Its catalogue add-ons extend the agent’s workflows and available tools.

moltis-org/moltis · 2,846 stars · on GitHub · moltis.org

Install

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.

Any agent
npx skills add moltis-org/moltis --skill himalaya
Clone the repo
git clone --depth 1 https://github.com/moltis-org/moltis

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for himalaya

README.md
[![agentmods](https://agentmods.dev/badge/skills/moltis-org/moltis/himalaya/github.svg)](https://agentmods.dev/skills/moltis-org/moltis/himalaya)
Your own site
<a href="https://agentmods.dev/skills/moltis-org/moltis/himalaya"><img src="https://agentmods.dev/badge/skills/moltis-org/moltis/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.

agentmods 80×15 button for himalaya

Your own site · 80×15
<a href="https://agentmods.dev/skills/moltis-org/moltis/himalaya"><img src="https://agentmods.dev/badge/skills/moltis-org/moltis/himalaya.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,116 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.01116
Opus 5 $0.00019 $0.00558
Sonnet 5 $0.00008 $0.00223
Haiku 4.5 $0.00004 $0.00112

Measured 9d ago against content hash 4751221c0e36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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 9d 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.

crates/skills/src/assets/email/himalaya/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Himalaya v2 Email CLI

Use this skill only with Himalaya major version 2. Its command and configuration syntax differs from v1.

References

  • references/configuration.md for v2 config paths, accounts, and backends.
  • references/message-composition.md for v2 compose and send flows.

Install and configure

Install a v2 build and verify it before continuing:

himalaya --version

Official installation options include Homebrew and the current Git repository:

brew install himalaya
cargo install --locked --git https://github.com/pimalaya/himalaya.git

If the package manager installs v1, use a v2 release or the Git installation. Run the v2 setup wizard with no subcommand:

himalaya

The wizard prints TOML that can be saved or merged into the config. There is no v2 account configure command. Check the result with:

himalaya --json account list
himalaya --account=work account check

Command conventions

Use v2's global account and backend selectors before the subcommand. Mailbox selectors belong to the leaf command:

himalaya --json --account=work --backend=imap envelope list --mailbox=INBOX
  • --json selects structured output; v2 does not use --output json.
  • --account and --backend are global selectors. --mailbox is a leaf-command option; these can also be written as -a, -b, and -m.
  • Shared read backends are imap, jmap, gmail, msgraph, maildir, and m2dir. SMTP sends messages; it does not fetch them.
  • Message IDs are mailbox-relative for some backends. Re-list after moving mail or changing mailboxes.

Read operations

List mailboxes and envelopes:

himalaya --json --account=work --backend=imap mailbox list
himalaya --json --account=work --backend=imap \
  envelope list --mailbox=INBOX --page=1 --page-size=20

Search with the v2 shared query language:

himalaya --json --account=work --backend=imap \
  envelope search --mailbox=INBOX -- \
  from [email protected] and subject meeting order by date desc

Read the full file on GitHub · 143 lines

Files

What ships with it

2 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.

Changes

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.

  1. 9d ago First seen · 143 lines · 39 tokens per session scan A 4751221c0e36

Subscribe to this mod's changes

himalaya is a skill published in the GitHub repository moltis-org/moltis (2,846 stars, last pushed 6d ago), licensed MIT. It adds 39 tokens to every session and 1,116 once invoked, about $0.0002 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 2026-08-30.