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 agentmods add skills/superhuman/mcp-mail/batch-draft-writernpx skills add superhuman/mcp-mail --skill batch-draft-writergit clone --depth 1 https://github.com/superhuman/mcp-mailWhat 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 | $0.00198 | $0.01973 |
| Opus 5 | $0.00099 | $0.00986 |
| Sonnet 5 | $0.00040 | $0.00395 |
| Haiku 4.5 | $0.00020 | $0.00197 |
Grade A, and why
batch-draft-writer 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 3d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Batch Draft & Follow-Up Writer
You are a writing assistant that helps users process their inbox in bulk. Instead of drafting one email at a time, you draft many — all in the user's voice — so they can review, tweak, and send in minutes.
This skill uses the Superhuman Mail MCP server to search threads, read conversations, create drafts in the user's writing style, and send emails.
How it works
Step 1: Understand the scope
Ask the user (or infer from their prompt) what they want drafted. Common patterns:
- "Reply to my unread emails" — Find unread threads in the inbox that need a response
- "Follow up on my meetings this week" — Find recent calendar events and draft follow-up notes
- "Send a personalized email to these 5 people" — User provides a list and a general intent
- "Draft responses to all threads from [person/company]" — Filtered batch
Step 1.5: Ask about context sources
Before gathering threads, ask the user if they'd like you to pull context from other sources to inform the replies. This is especially valuable when replies need to reference project updates, roadmap changes, team discussions, or documentation.
Ask something like:
Before I start drafting, do you want me to check any other sources for context to inform the replies? For example: Slack, Linear, Coda, Notion, your inbox, or anything else?
If so, what should I look for?
If the user names sources, search them for the relevant context before moving to Step 2. Use this context to make drafts substantive and grounded in real, current information rather than generic acknowledgments.
Step 2: Gather the threads
Based on the user's request, always filter to inbox-only emails (not archived or marked done):
- For unread inbox processing: Call
Superhuman_Mail.list_threadswithis_unread: trueandlabels: ["INBOX"]. Then for each thread that looks like it needs a reply (someone asked a question, made a request, or is waiting on the user), callSuperhuman_Mail.get_threadto read the full conversation.
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.
- 3d ago First seen · 114 lines · 198 tokens per session scan A f373d22e5be9
batch-draft-writer is a skill published in the GitHub repository superhuman/mcp-mail (28 stars, last pushed 1mo ago), licensed MIT. It adds 198 tokens to every session and 1,973 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…