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 Jansen611/Agent-Skills --skill himalaya-email-rustgit clone --depth 1 https://github.com/Jansen611/Agent-SkillsWrote 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/jansen611/agent-skills/himalaya-email-rust)<a href="https://agentmods.dev/skills/jansen611/agent-skills/himalaya-email-rust"><img src="https://agentmods.dev/badge/skills/jansen611/agent-skills/himalaya-email-rust/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/jansen611/agent-skills/himalaya-email-rust"><img src="https://agentmods.dev/badge/skills/jansen611/agent-skills/himalaya-email-rust.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 | $0.00095 | $0.02526 |
| Opus 5 | $0.00048 | $0.01263 |
| Sonnet 5 | $0.00019 | $0.00505 |
| Haiku 4.5 | $0.00010 | $0.00253 |
Grade B, and why
himalaya-email-rust scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 600 ~/.config/himalaya/config.toml ~/.config/himalaya/.env How it starts
The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Himalaya Email Manager
Manage email with Himalaya v2.0.0+. Primary: built-in v2 commands. For simple email attachments, use message compose --attach. For rich MIME, signing, encryption, or custom formatting, generate a valid .eml file and pass it to message send.
All commands are stateless. Check the installed binary's --help when a command or flag is version-sensitive.
Decision
- Check the binary and account first:
himalaya --versionandhimalaya account check --json. - For a normal text email or ordinary attachment, use Path A (
message compose). - For multipart MIME or custom headers, use Path B (
message sendwith.eml). - For Gmail SMTP, do not pass
--save sentunless a duplicate Sent copy is explicitly requested. Gmail normally saves sent messages automatically. - For machine processing, use
--jsonand keep the mailbox together with every message id.
Environment Check
command -v himalaya
himalaya --version
himalaya account list --json
himalaya account check --json
If Himalaya is not in PATH, check the common Cargo location:
test -x "$HOME/.cargo/bin/himalaya" && "$HOME/.cargo/bin/himalaya" --version
Install a stable release using the official release assets or installer. OAuth and secret storage are provided through external tools such as password managers and token brokers.
Official references:
Safety
- Never print, log, or include passwords, app passwords, OAuth tokens, or
.envcontents. - Verify the recipient, subject, body, and attachment paths before sending.
- Do not use
--save sentfor Gmail SMTP unless a manual Sent copy is required. - Use
--log-level offwhen clean JSON output is required.
Configuration
Config files are loaded from the first valid path among:
$XDG_CONFIG_HOME/himalaya/config.toml$HOME/.config/himalaya/config.toml$HOME/.himalayarc
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 First seen · 316 lines · 95 tokens per session scan B d05808b6bdfd
himalaya-email-rust is a skill published in the GitHub repository Jansen611/Agent-Skills (2 stars, last pushed 12d ago), licensed MIT. It adds 95 tokens to every session and 2,526 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.