email-operations

A workflow for working with email from supplied messages, files, or summaries. It can prepare drafts and follow-ups, but the input says it does not directly read or send mail through Gmail, Outlook, IMAP, or SMTP.

In plain words
What is it for?
Summarizing exported email, drafting replies or new messages, planning follow-ups, reviewing wording, and identifying missing mail integrations.
Why use it?
It avoids pretending to access an inbox or send a message when no native mail connection is available. It keeps drafts and summaries based on evidence you provide.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/codeinfinity1/stram/email-operations
Any agent
npx skills add CodeInfinity1/Stram --skill email-operations
Clone the repo
git clone --depth 1 https://github.com/CodeInfinity1/Stram

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 694 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00038 $0.00694
Opus 5 $0.00019 $0.00347
Sonnet 5 $0.00008 $0.00139
Haiku 4.5 $0.00004 $0.00069

Measured 2d ago against content hash e532f1b0e3fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

email-operations 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 2d 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/communications/email-operations/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Email Operations

Purpose

Support email work as a personal-assistant capability while respecting the current Stram native-tool boundary. Until a Stram-owned mail adapter exists, this skill drafts, summarizes, and plans email work from provided evidence instead of pretending to read or send mail directly.

When To Use

Use for email drafts, inbox summaries from pasted/exported email, follow-up wording, reply review, mail setup planning, or deciding what native mail tools need to be implemented.

Inputs And Evidence

  • Pasted email, exported .eml/text, thread summary, recipient list, subject, and desired tone.
  • Existing notes, meeting follow-ups, commitments, or relationship context.
  • User approval for any external-visible draft or send.
  • Native capability search/status output.

Tool Map

  • read_file
  • write_note
  • email_draft_prepare
  • gmail_draft_prepare
  • memory_write
  • cognitive_commitment_record
  • cognitive_trigger_record
  • tool_search
  • capability_surface
  • message-approval-policy

Workflow

  1. Determine whether the user needs summary, reply draft, new email, follow-up plan, or adapter implementation.
  2. Use only provided mail evidence unless a native mail adapter is added later.
  3. Extract sender, recipients, subject, dates, asks, commitments, deadlines, and risks.
  4. Draft concise emails with subject, greeting, body, ask, closing, and optional alternatives.
  5. Record commitments or reminders only when explicit and desired.
  6. For Gmail-style drafting, use gmail_draft_prepare with explicit recipients, subject, body, and reason; verify the draft artifact path.
  7. For real sending, report the missing native send adapter or route through a future Stram-owned email send tool with approval.

Native Implementation Boundaries

  • Do not use external reference Himalaya, Gmail scripts, external reference plugins, or external mail packages as the skill implementation.
  • Drafting is natively supported through Stram-owned draft artifact tools. Sending still requires a future Stram-owned Gmail/Outlook/IMAP/SMTP adapter with schemas, approvals, tests, and redaction.
  • Do not scrape a mail UI with OS/browser tools unless the user explicitly asks and approves that path.

Read the full file on GitHub · 75 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. 2d ago First seen · 75 lines · 38 tokens per session scan A e532f1b0e3fe

Subscribe to this mod's changes

email-operations is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 22d ago), licensed MIT. It adds 38 tokens to every session and 694 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.