channel-email

channel-email is a skill for Claude Code, Codex from moshthepitt/lionclaw. It costs 15 tokens per session (370 once invoked), scanned A, original, MIT.

An email channel worker that connects LionClaw to a mailbox and controls which messages can become tasks. It handles email login, sending, receiving, and held messages on the host system.

In plain words
What is it for?
It is for receiving approved emails, holding or releasing messages, fetching approved message bodies, and sending email through IMAP and SMTP or OAuth2.
Why use it?
It prevents unknown senders from silently creating work and keeps mailbox credentials and full message contents outside the runtime until approval.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for receiving approved emails, holding or releasing messages, fetching approved message bodies, and sending email through IMAP and SMTP or OAuth2.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/moshthepitt/lionclaw/channel-email
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 moshthepitt/lionclaw --skill channel-email
Clone the repo
git clone --depth 1 https://github.com/moshthepitt/lionclaw

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 channel-email

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

agentmods 80×15 button for channel-email

Your own site · 80×15
<a href="https://agentmods.dev/skills/moshthepitt/lionclaw/channel-email"><img src="https://agentmods.dev/badge/skills/moshthepitt/lionclaw/channel-email.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 370 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.
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 $0.00015 $0.00370
Opus 5 $0.00008 $0.00185
Sonnet 5 $0.00003 $0.00074
Haiku 4.5 $0.00002 $0.00037

Measured 11d ago against content hash 476ef69bde95, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

channel-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 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.

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.

skills/channel-email/SKILL.md · 34 lines

What it actually says

Email Channel

This skill runs the host-side Email channel worker. It owns mailbox auth, IMAP/SMTP transport, held-mail state, and provider-specific email handling. The runtime never receives mailbox credentials or OAuth tokens.

The channel admits only exact approved senders through LionClaw channel grants. Unknown mail is held or suppressed by the worker and must not become runtime work unless the local operator explicitly approves the sender or releases an authenticated held item. Full message bodies are fetched only after approval and are capped by EMAIL_MAX_MESSAGE_BYTES before any runtime work is queued.

Mailbox auth is either EMAIL_AUTH_MODE=basic with IMAP/SMTP passwords, or EMAIL_AUTH_MODE=xoauth2 with an absolute EMAIL_XOAUTH2_TOKEN_CMD; missing EMAIL_AUTH_MODE defaults to basic for legacy configs. The normal OAuth2 setup path is lionclaw connect email <provider> ..., which runs this channel's setup helper from the installed channel snapshot. The channel binary also exposes the lower-level oauth2 setup and oauth2 token commands; token refresh runs host-side without a shell and prints only a short-lived access token to stdout. Refresh-token state remains outside runtime projection.

This channel package also carries the runtime-facing email Agent Skill at runtime/email/. LionClaw projects that facet into runtimes when this skill is bound as the email channel, while keeping the host-side channel package and mail transport credentials out of the runtime.

Detailed architecture, setup, QA, one-shot release behavior, and packaged asset notes for this channel live in README.md in this skill directory.

Files

What ships with it

5 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. 11d ago First seen · 34 lines · 15 tokens per session scan A 476ef69bde95

Subscribe to this mod's changes

channel-email is a skill published in the GitHub repository moshthepitt/lionclaw (16 stars, last pushed 9d ago), licensed MIT. It adds 15 tokens to every session and 370 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 2026-08-30.