inbox-cleanup

inbox-cleanup is a skill for Claude Code from HybridAIOne/hybridclaw. It costs 64 tokens per session (684 once invoked), scanned A, original, MIT.

An inbox-cleanup tool that finds newsletters, promotions, and notifications and can archive selected groups in bulk after the user approves a plan.

In plain words
What is it for?
It is for planning and applying bulk archiving, reviewing the largest sender groups, and undoing an archive operation.
Why use it?
It reduces clutter in crowded inboxes without deleting messages, and archived mail can be undone for 30 days.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit It is for planning and applying bulk archiving, reviewing the largest sender groups, and undoing an archive operation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hybridaione/hybridclaw/inbox-cleanup
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 HybridAIOne/hybridclaw --skill inbox-cleanup
Clone the repo
git clone --depth 1 https://github.com/HybridAIOne/hybridclaw

Made for: Claude Code.

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 inbox-cleanup

README.md
[![agentmods](https://agentmods.dev/badge/skills/hybridaione/hybridclaw/inbox-cleanup/github.svg)](https://agentmods.dev/skills/hybridaione/hybridclaw/inbox-cleanup)
Your own site
<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/inbox-cleanup"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/inbox-cleanup/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 inbox-cleanup

Your own site · 80×15
<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/inbox-cleanup"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/inbox-cleanup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 684 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 $0.00064 $0.00684
Opus 5.5 $0.00026 $0.00274
Sonnet 5.5 $0.00013 $0.00137
Haiku 4.5 $0.00006 $0.00068

Measured 7d ago against content hash 1f3981f75d85, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

inbox-cleanup 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 7d 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/inbox-cleanup/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Inbox Clean-up

You can archive mail in bulk with inbox_cleanup. You cannot delete mail, and you never try to.

How

  1. Call inbox_cleanup with action: plan. It looks at the newest inbox mail by sender and mail headers and changes nothing.
  2. Say in one or two sentences what it found: how many emails it can archive and the two or three biggest senders. The card shows the rest, so don't list every group.
  3. Call action: apply with the plan's preselected groups. The user sees a card with the groups and decides there. Add a group the plan did not preselect, or leave one out, only when the user asks ("keep the Club mails").
  4. Report the numbers from the result: archived, skipped and why, not moved. Say once that undo works for 30 days. If the result has stopped_because, say what moved before it stopped.
  5. When the user wants it back, call action: undo with the same plan_id.

Rules

  • Mail moves only through inbox_cleanup. Never use the browser, a script or the shell to move, flag or delete mail, even if the user asks. That is how accounts get locked and mail gets lost.
  • If the user asks you to delete, empty the trash or remove mail for good, say that you only archive: archived mail is out of the inbox and never expires. If they still want it gone, they can delete the Archive folder's mail in their mail app themselves.
  • Never decide by words in a subject. "Offer", "invoice" or "deal" says nothing about who sent it. Trust the plan's groups.
  • Never say you read or checked emails you did not open. Say you sorted them "by sender and mail headers", because that is what the plan does.
  • Numbers come from tool results. If the plan says 2,140, don't round it.
  • The plan leaves alone mail from people the user writes to, starred mail, senders the user replied to, this week's mail and mail without bulk headers. Don't offer to include them.
  • A weekly tidy-up is a scheduled task that runs plan and tells the user what it found. It never archives without the user approving the card.
  • If plan or apply says the mailbox can't do it (no Archive folder, a server that can't report moves), say so in one sentence and stop. Don't try another way.

Read the full file on GitHub · 58 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. 7d ago First seen · 58 lines · 64 tokens per session scan A 1f3981f75d85

Subscribe to this mod's changes

inbox-cleanup is a skill published in the GitHub repository HybridAIOne/hybridclaw (159 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 684 once invoked, about $0.0003 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 2026-10-10.