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 darellchua2/opencode-config-template --skill email-drafter-skillgit clone --depth 1 https://github.com/darellchua2/opencode-config-templateWrote 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/darellchua2/opencode-config-template/email-drafter-skill)<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/email-drafter-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/email-drafter-skill/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/darellchua2/opencode-config-template/email-drafter-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/email-drafter-skill.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 | $0.00070 | $0.01285 |
| Opus 5.5 | $0.00028 | $0.00514 |
| Sonnet 5.5 | $0.00014 | $0.00257 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade A, and why
email-drafter-skill 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 1mo 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Email drafter
Write emails the recipient reads once and knows what to do. The test: a busy person can answer "what does this email want from me, by when?" within five seconds of opening it.
Process
- Collect the brief: recipients, relationship, purpose, the facts, the ask, any date. Missing a fact? Ask, or bracket it
[like this]— never invent names, numbers, dates, or terms. - Find the voice: if an earlier email from the thread or the sender is in context, mirror its greeting, sign-off, formality, and structure. A reply to a numbered list answers by the same numbers. A thread that uses plain prose gets plain prose back.
- Draft using the frames below.
- Run the slop checklist.
- Deliver the draft, then 1–3 bullets stating assumptions made and decisions left open — outside the email, never inside it.
Subject line
- Front-load the concrete subject and the date when one exists: "Slope Checker — status update and site testing on 16 September".
- Banned: "Update", "Following up", "Touching base", "Quick question", curiosity-gap teasers, ALL CAPS, emoji.
- In a thread, keep the subject unless the topic changed; if it changed, start a new thread instead of hijacking the old one.
Openings
- The first line does work: it answers, states the point, or acknowledges what triggered the email ("Thank you for your patience since our last update.").
- Never open with weather-talk: "I hope this email finds you well", "I trust you are well", "I hope you're having a great week". Delete it and start with the point.
- Apology discipline: one acknowledgment line for a delay ("Thank you for your patience"). One. No relitigating causes, no repeating the apology at the end.
Structure
New email: purpose in the first line → context → details → one ask with a date → sign-off.
Reply (answer first): the answer goes in the first sentence, context after. The recipient should not wade through background to find out the answer is "yes, Thursday works".
Multi-question reply: mirror their structure — same numbers, or quote each line and answer under it. Answer every question; before delivering, reread the incoming email against the draft and check nothing was skipped.
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.
- 1mo ago First seen · 80 lines · 70 tokens per session scan A 07dd3c47ed0c
email-drafter-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed 28d ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,285 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 2026-09-10.
Other skills, from other repositories
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
one-three-one-rule
1-3-1 decision briefs: problem, three options, one pick.
simplified-english
Write user-facing comments, plans, and documents in ASD-STE100 Simplified Technical English — short, unambiguous sentences with approved words and one meaning each — so readers understand them the first time.
messenger_read
Work with the user's Messenger account: read call history; read and search contacts; read, search, and summarize conversations; send, react to, unsend, or edit messages; and message Marketplace listing threads.
bug-reporting-excellence
Write high-quality bug reports that get fixed quickly. Use when reporting bugs, training teams on bug reporting, or establishing bug report standards.
novu-inbox-integration
Integrate Novu's in-app notification inbox into web applications. Supports React, Next.js, and vanilla JavaScript. Includes the Inbox component (bell icon + notification feed), composable components (Bell, Notifications, InboxContent, Preferences), headless hooks, branded theming, custom render props, multi-tenancy…