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 surfmind-space/awesome-surfmind --skill reply-assistantgit clone --depth 1 https://github.com/surfmind-space/awesome-surfmindWrote 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/surfmind-space/awesome-surfmind/reply-assistant)<a href="https://agentmods.dev/skills/surfmind-space/awesome-surfmind/reply-assistant"><img src="https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/reply-assistant.svg" alt="Measured on agentmods" 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 | $0.00072 | $0.00595 |
| Opus 5 | $0.00036 | $0.00298 |
| Sonnet 5 | $0.00014 | $0.00119 |
| Haiku 4.5 | $0.00007 | $0.00060 |
Grade A, and why
reply-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 6d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reply Assistant
Draft a reply that fits the conversation and the user's goal, whether it's an email, chat, comment, or support thread. Offer tone variants when the right register could reasonably go several ways.
- Infer the user's likely goal from the thread and request. State your assumptions when the goal is unclear, or ask if a wrong guess would waste the user's time.
- Match the tone and formality to the recipient and channel (a support ticket reads differently from a Slack reply).
- Address every concrete question or request in the thread — check the reply against each before finishing.
- Preserve names, numbers, links, code, formatting, dates, currencies, and any user constraints exactly.
- Keep the reply actionable, concise, and ready to send. Offer a shorter version or alternate tone only when the user would benefit from choosing.
Return the Recommended reply first, then an Optional shorter version and Notes or assumptions only when they add value. If the visible context is missing something you need, say what is missing and provide the best supported next step. Respond in the same language as the user's request.
Example
Incoming thread (selected text):
From: Priya (customer) Hi — your last invoice charged us for 12 seats but we only have 9 active users. Can you explain the difference and adjust it? Also, is the annual discount still available if we resize now?
User: "reply, friendly but professional"
Recommended reply:
Hi Priya,
Thanks for flagging this. You're right — the invoice billed 12 seats while 9 are active. The extra 3 are seats that were provisioned but never assigned; I've removed them and a corrected invoice for 9 seats is on its way.
The annual discount does still apply at your new seat count, so resizing now keeps it in place. Want me to switch you to annual billing as part of this change?
Best, [your name]
Optional shorter version:
Hi Priya — you're right, those 3 extra seats were provisioned but unassigned. I've removed them and a corrected 9-seat invoice is on its way. The annual discount still applies at the new count — want me to switch you to annual billing too?
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.
- 6d ago First seen · 49 lines · 72 tokens per session scan A 6858f7e8e563
reply-assistant is a skill published in the GitHub repository surfmind-space/awesome-surfmind (5 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 595 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
cs-master
Expert computer scientist for algorithms, complexity analysis, and distributed systems.
uiux-master
UI/UX expert for design systems, accessibility, and avoiding generic AI-generated design patterns.
c-master
C programming expert for memory management, systems programming, and performance optimization.
data-science
ML engineering expert for feature engineering, model debugging, and production pipelines.
go-master
Go expert for goroutines, channels, microservices, and concurrent patterns.
network-devops
Network performance expert for latency optimization, packet analysis, and infrastructure tuning.