send-with-identity

send-with-identity is a skill for Claude Code, Codex from googlarz/proton-mail-bridge-client. It costs 58 tokens per session (978 once invoked), scanned A, original, MIT.

An email-sending safeguard for setups with more than one account or email signature. Before sending, replying, forwarding, scheduling or creating a sendable draft, it asks which address and signature to use.

In plain words
What is it for?
Use it when sending or drafting email through the Proton Mail bridge, especially for replies and forwards involving multiple accounts.
Why use it?
It prevents messages from being sent from the wrong account or with an unintended signature. It also makes the chosen sender explicit instead of relying on a default.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions Claude Code.

Good fit Use it when sending or drafting email through the Proton Mail bridge, especially for replies and forwards involving multiple accounts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/googlarz/proton-mail-bridge-client/send-with-identity
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 googlarz/proton-mail-bridge-client --skill send-with-identity
Clone the repo
git clone --depth 1 https://github.com/googlarz/proton-mail-bridge-client

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 send-with-identity

README.md
[![agentmods](https://agentmods.dev/badge/skills/googlarz/proton-mail-bridge-client/send-with-identity/github.svg)](https://agentmods.dev/skills/googlarz/proton-mail-bridge-client/send-with-identity)
Your own site
<a href="https://agentmods.dev/skills/googlarz/proton-mail-bridge-client/send-with-identity"><img src="https://agentmods.dev/badge/skills/googlarz/proton-mail-bridge-client/send-with-identity/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 send-with-identity

Your own site · 80×15
<a href="https://agentmods.dev/skills/googlarz/proton-mail-bridge-client/send-with-identity"><img src="https://agentmods.dev/badge/skills/googlarz/proton-mail-bridge-client/send-with-identity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 978 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 $0.00058 $0.00978
Opus 5.5 $0.00023 $0.00391
Sonnet 5.5 $0.00012 $0.00196
Haiku 4.5 $0.00006 $0.00098

Measured 9d ago against content hash 5036be743f2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

send-with-identity 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.

skills/send-with-identity/SKILL.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Send with a chosen address and signature

A mail must never go out from a guessed address or with a guessed signature. This skill adds the rule the server cannot enforce by itself: ask first.

Rule

Before ANY send, reply, forward or schedule (and before creating a draft that will be sent):

  1. Ask which address to send from, unless the user already named it in this request. List the configured accounts (list_accounts). For a reply or forward, suggest the account the original message arrived in (an emailId prefixed <slug>:: belongs to that account; a plain id is the primary) and let the user confirm.
  2. Ask which signature to use: the one saved for that address below, or none. If none is saved for it, say so and ask whether to send without one.
  3. Pass the choice explicitly. What each tool takes (checked against the server's tool schemas):
    • Immediate sends (send_email, reply_to_email, reply_all_email, forward_email): from: "<address>" sends as that address (without it, a reply or forward goes out from the account the original message arrived in). These four are the only tools with appendSignature (default true): write the signature into the body yourself and set appendSignature: false, so the server's global PROTONMAIL_SIGNATURE (if set) is not added on top and the signature does not appear twice. An HTML signature needs isHtml: true on the call.
    • Drafts (create_draft, create_reply_draft, create_forward_draft, create_thread_reply_draft, update_draft): the server never adds PROTONMAIL_SIGNATURE to a draft, and these tools have no appendSignature. Put the chosen signature into the draft body yourself (with isHtml: true for an HTML signature), or leave it out for "none". On create_draft and update_draft from is the address the draft is sent as. On create_reply_draft, create_forward_draft and create_thread_reply_draft from only selects which configured account STORES the draft (it falls back to the primary account if unknown), so to change the sending address of such a draft call update_draft with from afterwards and confirm it with get_draft.
    • Sending a saved draft (send_draft, schedule_draft): neither takes from, appendSignature or a body. Whatever the draft holds is sent, so settle the address and signature on the draft first, and tell the user the draft's address and signature before sending. A signature is not added at send time.
  4. The user's explicit "yes" on the final recipients, subject and body is still required. Choosing an address or signature is not that approval.

Read the full file on GitHub · 42 lines

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 Changed · +1 lines 5036be743f2e
  2. 15d ago First seen · 41 lines · 58 tokens per session scan A ef82ea6a9c1d

Subscribe to this mod's changes

send-with-identity is a skill published in the GitHub repository googlarz/proton-mail-bridge-client (73 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 978 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 2026-10-01.

Related

Other skills, from other repositories

erga-mcp

Use immediately when a user shares a job-posting URL—including a bare link or chat preview—and when organizing recruiting records, evaluating career evidence, or proposing a truthful résumé update through Erga MCP.

Adr1an04/erga-mcp · 44 tokens

work-assistant

Usa un'istanza configurata di Work Assistant tramite MCP o CLI per ispezionare caselle, costruire conoscenza locale e preparare candidati di risposta. Non usare per client email non collegati a Work Assistant.

Wulfgardr/work-assistant · 52 tokens

triage

Work a Gmail inbox with mailwarden — search, bulk actions, snooze, unsubscribe and recurring checks, with the rules that keep a bulk action from touching mail the user never meant to touch. Use when the user asks to triage, clean up, archive, label, snooze or unsubscribe from mail through mailwarden, before any…

csitte/mailwarden · 96 tokens

redpill

Use when: an operator asks to install, configure, explain, audit, or use the redpill MCP tools for reflection, conversation, local mail, or an explicitly enabled task decline.

sergey-goncharenko/redpill-mcp · 40 tokens

readndraft-email

Safely search, read, flag, move, and draft email with the readNdraft IMAP MCP. Use when a user asks to find or read mail, retrieve an attachment, star or change read state, move selected messages between ordinary mailboxes, or create or update a draft without sending it.

LeoPhoenixT/readNdraft-imap-mcp · 66 tokens

sentfromai

Give this agent its own email address — create inboxes, send, reply in-thread, search mail, and manage senders via SentFromAI.

samuelar2/sentfromai-mcp · 33 tokens