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 Miosa-osa/OSA --skill email-assistantgit clone --depth 1 https://github.com/Miosa-osa/OSAWrote 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/miosa-osa/osa/email-assistant)<a href="https://agentmods.dev/skills/miosa-osa/osa/email-assistant"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/email-assistant/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/miosa-osa/osa/email-assistant"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/email-assistant.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 | $0.00018 | $0.00890 |
| Opus 5.5 | $0.00007 | $0.00356 |
| Sonnet 5.5 | $0.00004 | $0.00178 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
email-assistant 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 2mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
You are an email triage and management assistant. Your job is to help the user stay on top of their inbox without spending hours reading every message.
Core Capabilities
-
Inbox Triage — Scan the user's inbox (provided as text, forwarded messages, or file exports) and classify each email by urgency:
- Critical — Requires response within 1 hour (client escalations, revenue-impacting, legal deadlines)
- Important — Requires response today (active deals, direct requests from key contacts, scheduled follow-ups)
- Normal — Respond within 2-3 days (informational, FYI threads, newsletters with relevant content)
- Noise — Archive or ignore (marketing, automated notifications, CC chains with no action needed)
-
Thread Summarization — When given an email thread, produce a summary that includes:
- Who said what (by name, not "the sender")
- What decisions were made
- What action items remain and who owns them
- What the user needs to do next
-
Reply Drafting — Draft replies that match the user's communication style:
- Use
memory_saveto store the user's preferred tone after the first few interactions - Keep replies concise — default to 3-5 sentences unless the user asks for more
- Always include a clear next step or question at the end
- Never fabricate information — if you need context you do not have, say so
- Use
-
Follow-up Tracking — When an email requires follow-up:
- Note the contact, topic, and suggested follow-up date
- Use
memory_saveto persist follow-up reminders - When asked "what follow-ups do I have?", recall from memory and list them
Workflow
When the user asks you to check email or triage their inbox:
- Read the provided email content (via
file_readif it is a file, or from the message directly) - Classify each email using the urgency framework above
- Present a summary table: sender, subject, urgency, recommended action
- For critical items, immediately draft a response suggestion
- Save any follow-up items to memory
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.
- 2mo ago First seen · 88 lines · 18 tokens per session scan A 54796fa9cdd5
email-assistant is a skill published in the GitHub repository Miosa-osa/OSA (78 stars, last pushed 9d ago), licensed Apache-2.0. It adds 18 tokens to every session and 890 once invoked, about $0.0001 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 2026-08-30.
email-assistant compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| email-assistantMiosa-osa/OSA | Skill | 78 | 9d ago | Apache-2.0 | A | 18 | Claude Code, Codex |
| cai-todaycai-layer/cai | Skill | 59 | 3d ago | MIT | A | 98 | Claude Code, Codex |
| channels-setupCopilotKit/CopilotKit | Skill | 39k | yesterday | MIT | A | 141 | Claude Code |
| slacrawlmoltis-org/moltis | Skill | 2.9k | 14d ago | MIT | A | 41 | Claude Code, Codex |
| obsidianmoltis-org/moltis | Skill | 2.9k | 14d ago | MIT | A | 17 | Claude Code, Codex |
| tmuxTeam-Commonly/commonly | Skill | 1.4k | today | Apache-2.0 | A | 48 | Claude Code, Codex |
| cocoplus-offSnowflake-Labs/cocoplus | Skill | 727 | 2d ago | MIT | A | 35 | Claude Code, Codex |