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 isaacrowntree/claude-social-skills --skill himalaya-emailgit clone --depth 1 https://github.com/isaacrowntree/claude-social-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/isaacrowntree/claude-social-skills/himalaya-email)<a href="https://agentmods.dev/skills/isaacrowntree/claude-social-skills/himalaya-email"><img src="https://agentmods.dev/badge/skills/isaacrowntree/claude-social-skills/himalaya-email/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/isaacrowntree/claude-social-skills/himalaya-email"><img src="https://agentmods.dev/badge/skills/isaacrowntree/claude-social-skills/himalaya-email.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 | $0.00039 | $0.01301 |
| Opus 5 | $0.00019 | $0.00651 |
| Sonnet 5 | $0.00008 | $0.00260 |
| Haiku 4.5 | $0.00004 | $0.00130 |
Grade A, and why
himalaya-email 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 12d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Himalaya Email CLI
Use himalaya (v1.2.0) for all email operations. The user's account should be configured in ~/Library/Application Support/himalaya/config.toml.
When to Use
- User asks about emails, inbox, or messages
- User wants to read, search, or list emails
- User wants to trace email origin or check headers
- User mentions a sender or subject and wants to find/read the email
Core Commands
# List recent emails (default: INBOX)
himalaya envelope list --page-size 20
# List emails in a specific folder
himalaya envelope list --folder "Sent" --page-size 20
# Read an email by ID (marks as seen)
himalaya message read <ID>
# Read without marking as seen (preview mode)
himalaya message read -p <ID>
# Read with no headers (body only)
himalaya message read --no-headers <ID>
# Read with specific headers visible
himalaya message read -H "From" -H "To" -H "Subject" -H "Date" <ID>
# Search/filter envelopes (if supported by backend)
himalaya envelope list --page-size 50
Tracing Email Origin / Headers
When the user wants to know where an email came from, read it with authentication headers:
himalaya message read -p \
-H "From" \
-H "Reply-To" \
-H "Return-Path" \
-H "Received" \
-H "X-Originating-IP" \
-H "Authentication-Results" \
-H "Received-SPF" \
-H "DKIM-Signature" \
-H "ARC-Authentication-Results" \
-H "Message-ID" \
-H "X-Mailer" \
<ID>
How to Interpret Headers
- SPF (Sender Policy Framework):
spf=passmeans the sending IP is authorized by the domain. Look for the IP inReceived-SPF. - DKIM (DomainKeys Identified Mail):
dkim=passmeans the email signature is valid and the content wasn't tampered with. Checkheader.d=for the signing domain. - DMARC:
dmarc=passmeans the domain's SPF/DKIM alignment policy passed. - ARC (Authenticated Received Chain): Shows authentication survived forwarding.
- Return-Path: The actual envelope sender (where bounces go).
- Received headers: Read bottom-to-top to trace the email's path through servers.
- Message-ID: Unique identifier; the domain after
@often reveals the originating mail system. - X-Originating-IP: If present, the sender's actual IP address.
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.
- 12d ago First seen · 138 lines · 39 tokens per session scan A ac790d4552b6
himalaya-email is a skill published in the GitHub repository isaacrowntree/claude-social-skills (4 stars, last pushed 12d ago), licensed MIT. It adds 39 tokens to every session and 1,301 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 2026-08-31.
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…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
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.