email-management

email-management is a skill for Claude Code, Codex from furkangonel/cowrangler. It costs 19 tokens per session (1,281 once invoked), scanned A, original, MIT.

A structured method for processing email by deciding whether each message should be deleted, delegated, handled immediately, or deferred to a later task.

In plain words
What is it for?
Triage incoming mail, set up folders or labels, schedule review batches, forward work to others, reply to quick requests, and move longer tasks into a task manager.
Why use it?
It prevents an inbox from becoming an untracked task list and reduces the distraction of checking messages continuously.

Skill for Claude CodeCodex

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

Good fit Triage incoming mail, set up folders or labels, schedule review batches, forward work to others, reply to quick requests, and move longer tasks into a task manager.

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

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 email-management

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/furkangonel/cowrangler/email-management"><img src="https://agentmods.dev/badge/skills/furkangonel/cowrangler/email-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,281 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 $0.00019 $0.01281
Opus 5 $0.00010 $0.00641
Sonnet 5 $0.00004 $0.00256
Haiku 4.5 $0.00002 $0.00128

Measured 10d ago against content hash a53168b8d147, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

email-management 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 10d 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.

bundled_skills/email/email-management/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Email Management SOP

Goal

Process email systematically so the inbox stays clear, nothing falls through the cracks, and email doesn't bleed into deep work time.

Core Principle: 4D Triage

For every email, apply exactly one action immediately:

Decision When Action
Delete Newsletters, FYIs, CC'd you unnecessarily Archive or delete immediately
Delegate Someone else should own this Forward with clear ask, move to "Waiting"
Do Takes under 2 minutes Reply now, then archive
Defer Needs thought, research, or specific time Move to task manager or snooze

Rule: Never leave an email in the inbox after making a decision.

Batch Processing Schedule

Do not check email continuously. Batch to 2-3 times per day:

Time Purpose
Morning (9am) Full triage — clear inbox, action urgent items
Midday (12-1pm) Quick scan — replies only, no new tasks
EOD (5pm) Final sweep — defer anything not done today

Turn off push notifications. Check on your schedule.

Folder / Label Taxonomy

Inbox                     ← Only unprocessed email lives here
├── Action                ← Needs reply or action from you
├── Waiting               ← Delegated; waiting on others
├── Reference/
│   ├── Finance           ← Invoices, receipts, contracts
│   ├── HR                ← Offer letters, benefits, onboarding
│   ├── Projects/         ← One subfolder per active project
│   └── Personal          ← Non-work reference
└── Archive               ← Everything else (searchable, not filed)

Key rule: Archive aggressively. The search bar is more reliable than folder filing.

Email Rules / Filters to Set Up

Automate triage with filters (Gmail, Outlook, Apple Mail all support this):

Rule: Newsletter/marketing
  FROM contains: unsubscribe | noreply | newsletter | digest
  → Skip inbox, label "Newsletter", mark read

Rule: CC'd only
  TO does not contain: [your email]
  → Skip inbox, label "CC", mark read

Rule: GitHub/Linear/Jira notifications
  FROM: [email protected] | linear.app | jira
  → Skip inbox, label "Dev Tools", mark read

Rule: Calendar invites
  Contains: .ics attachment OR subject contains "invitation"
  → Keep in inbox (needs action)

Rule: Receipts
  FROM: receipt | invoice | order | billing
  → Label "Finance/Receipts", mark read

Read the full file on GitHub · 172 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. 10d ago First seen · 172 lines · 19 tokens per session scan A a53168b8d147

Subscribe to this mod's changes

email-management is a skill published in the GitHub repository furkangonel/cowrangler (2 stars, last pushed 3d ago), licensed MIT. It adds 19 tokens to every session and 1,281 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 2026-08-31.