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.
npx skills add n24q02m/claude-plugins --skill inbox-reviewgit clone --depth 1 https://github.com/n24q02m/claude-pluginsWrote 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.
[](https://agentmods.dev/skills/n24q02m/claude-plugins/inbox-review)<a href="https://agentmods.dev/skills/n24q02m/claude-plugins/inbox-review"><img src="https://agentmods.dev/badge/skills/n24q02m/claude-plugins/inbox-review/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.
<a href="https://agentmods.dev/skills/n24q02m/claude-plugins/inbox-review"><img src="https://agentmods.dev/badge/skills/n24q02m/claude-plugins/inbox-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00020 | $0.00836 |
| Opus 5 | $0.00010 | $0.00418 |
| Sonnet 5 | $0.00004 | $0.00167 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
inbox-review 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.
This is a copy
100% identical to inbox-review — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inbox Review
Systematic morning inbox review with email-specific intelligence.
Multi-Account Handling
Always iterate ALL configured accounts, not just the default:
# List folders for all accounts first
folders(action="list")
# Then search each account
messages(action="search", query="UNSEEN", account="[email protected]")
messages(action="search", query="UNSEEN", account="[email protected]")
Never assume a single account. Users with EMAIL_CREDENTIALS containing multiple accounts expect all to be checked.
IMAP Search Syntax
Use proper IMAP search criteria -- these are NOT free-text queries:
| Intent | Correct syntax | Wrong (will fail or return wrong results) |
|---|---|---|
| Unread emails | UNSEEN |
unread, is:unread |
| Since a date | SINCE 2026-03-20 |
after:2026-03-20, date>2026-03-20 |
| From a sender | FROM [email protected] |
from:sender, [email protected] |
| Flagged/starred | FLAGGED |
starred, is:starred |
| With subject | SUBJECT "meeting notes" |
subject:meeting |
| Combine criteria | UNSEEN SINCE 2026-03-20 |
UNSEEN AND SINCE 2026-03-20 (no AND keyword) |
| Unread + from | UNSEEN FROM [email protected] |
UNSEEN AND FROM [email protected] |
IMAP criteria are space-separated (implicit AND). There is no explicit AND/OR keyword in basic IMAP search.
Thread Grouping
Group messages by conversation, not individual emails:
- Fetch unread messages
- Group by Subject line (strip
Re:,Fwd:prefixes, normalize whitespace) - Within each thread, sort by date ascending
- Display thread with message count: "Meeting Q2 Planning (4 messages, latest from Alice 2h ago)"
This prevents showing 10 individual replies to the same thread as 10 separate items.
Priority Classification
Classify based on recipient role and sender signals:
| Signal | Priority | Reasoning |
|---|---|---|
You are in To: field |
Action Required | Direct request to you |
You are in CC: field |
FYI | Informational, no action expected |
| Mailing list headers present | Low | Bulk/automated |
Reply-To differs from From |
Low | Likely automated/newsletter |
Known sender + To: you directly |
High | Personal direct message |
noreply@, notifications@ |
Low | System notification |
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.
- 11d ago First seen · 92 lines · 20 tokens per session scan A 04d233912dd5
inbox-review is a skill published in the GitHub repository n24q02m/claude-plugins (4 stars, last pushed today), licensed Apache-2.0. It adds 20 tokens to every session and 836 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to inbox-review, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
career-portfolio
A portfolio-building skill for Korean job seekers that organizes projects and explains their work for development, design, marketing, and planning roles.
marketing-meta-ads-manager
A skill that manages Facebook and Instagram advertising through Meta’s official connector using natural-language instructions.
hr-operations
A skill for designing remote-work and team-operation policies. It covers flexible work, asynchronous communication, collaboration tools, productivity tracking, and employee experience.
collab-conflict
A guide for handling difficult workplace colleagues and recurring communication conflicts.
collab-feedback-loop
A guide for giving and receiving workplace feedback about specific actions and their effects.
collab-meeting
A meeting facilitation aid that helps define the purpose, plan the agenda, guide discussion, record decisions, and assign follow-up actions.