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 gyanranjan/polyagent-skills --skill mail-summarizergit clone --depth 1 https://github.com/gyanranjan/polyagent-skillsWrote 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/gyanranjan/polyagent-skills/mail-summarizer)<a href="https://agentmods.dev/skills/gyanranjan/polyagent-skills/mail-summarizer"><img src="https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/mail-summarizer/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/gyanranjan/polyagent-skills/mail-summarizer"><img src="https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/mail-summarizer.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 | $0.00076 | $0.00821 |
| Opus 5 | $0.00038 | $0.00411 |
| Sonnet 5 | $0.00015 | $0.00164 |
| Haiku 4.5 | $0.00008 | $0.00082 |
Grade A, and why
mail-summarizer 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mail Summarizer
Purpose
Process email content to extract key information, summarize threads, identify action items, and draft contextually appropriate replies.
When to Use
- User shares an email and wants a summary
- User has a long email thread to understand quickly
- User needs action items extracted from emails
- User wants help drafting a reply
- User asks "what does this email say" or "what do they want"
When NOT to Use
- User wants to write a new email from scratch (that's general writing)
- User needs formal document analysis (use
document-analyzer)
Inputs
Required:
- Email content — the email text or thread
Optional:
- Context — user's role, relationship with sender, project context
- Reply intent — what the user wants to convey in their reply
- Tone preference — formal, casual, firm, diplomatic, etc.
Process
Step 1: Parse the Email
Identify:
- Sender and recipients (and their likely roles)
- Subject and core topic
- Thread order (if multiple emails)
- Tone of the communication (urgent, routine, escalation, etc.)
Step 2: Summarize
Produce a structured summary:
**From:** [sender]
**Subject:** [subject]
**TL;DR:** [1-2 sentence summary of the key point]
**Key Points:**
1. [Point 1]
2. [Point 2]
**Action Items:**
- [ ] [Action] — Owner: [who] — By: [when, if stated]
**Decisions Made:**
- [Decision, if any]
**Tone/Urgency:** [assessment]
Step 3: Draft Reply (if requested)
If the user wants a reply:
- Ask for reply intent if not provided ("What do you want to say back?")
- Match the formality level of the original email
- Address all action items or questions from the original
- Keep it concise — emails should be scannable
- Offer 2 variants if the situation is nuanced (e.g., firm vs diplomatic)
Step 4: Deliver
- For summary only: deliver the structured summary
- For reply: deliver the summary + draft reply
- Apply formatting from
common-skills/output-formatting.md
Output Format
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.
- 9d ago First seen · 111 lines · 76 tokens per session scan A 63db7cb47866
mail-summarizer is a skill published in the GitHub repository gyanranjan/polyagent-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 76 tokens to every session and 821 once invoked, about $0.0004 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.
Other skills, from other repositories
novu-design-workflow
Design notification workflows the Novu way — choose channels, set severity, decide when a workflow is critical, configure digests, and route based on subscriber state. Applies to BOTH dashboard-authored and code-first (@novu/framework) workflows. Use when planning a new workflow, deciding which channels to include…
human-cli
Reach the actual human you're working for via the human CLI (ask/approve/choose/tell) when you need a decision, approval, or notification and no one is watching this terminal right now. Use for background/autonomous/scheduled runs, risky or irreversible actions, and genuine multi-way ambiguity — not for routine…
novu-manage-preferences
Configure notification preferences in Novu at the workflow and subscriber level. Set default channel preferences (email, SMS, push, chat, in-app), mark preferences as read-only or subscriber-editable, and manage subscriber-specific overrides. Use when setting up notification opt-in/opt-out, configuring per-channel…
gmail-tool
Gmail integration tool for unread checks, reading bodies, and drafts via OAuth2 Gmail API access. Use when: reading inbox mail, fetching message bodies, writing drafts, or searching labeled mail.
Send emails directly from your agent. Supports HTML and plain text. Works with Unosend (5,000 free emails/month) or any SMTP provider.
imap-smtp-email
Read, search, and manage email via IMAP protocol. Send email via SMTP. Supports Gmail, Outlook, 163.com, 126.com, QQ Mail, and any standard IMAP/SMTP server with multi-account support.