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 ur-grue/autopunk-media-skills --skill referral-copy-writergit clone --depth 1 https://github.com/ur-grue/autopunk-media-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/ur-grue/autopunk-media-skills/referral-copy-writer)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/referral-copy-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/referral-copy-writer/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/ur-grue/autopunk-media-skills/referral-copy-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/referral-copy-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.01331 |
| Opus 5 | $0.00024 | $0.00665 |
| Sonnet 5 | $0.00010 | $0.00266 |
| Haiku 4.5 | $0.00005 | $0.00133 |
Grade A, and why
referral-copy-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 8d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Referral Copy Writer
What This Skill Does
Writes the in-email referral section that asks existing subscribers to share the newsletter with colleagues or friends — including the ask, the framing of the reward or reciprocity, and the specific share copy subscribers can use verbatim.
When To Use This Skill
- You are integrating a referral programme (such as SparkLoop, Beehiiv referrals, or a manual tracking system) and need copy for the in-newsletter ask
- You want to add an occasional organic sharing prompt to your newsletter without a formal referral programme
- Your subscriber growth has plateaued from your own channels and you want to activate word-of-mouth from your existing list
- You are launching a new referral tier or changing reward levels and need fresh copy to announce it
What You Need To Provide
Required: Newsletter name, voice, and audience; whether you are running a formal referral programme with rewards or just asking for organic sharing Optional: The specific rewards you offer at each referral tier (e.g. "3 referrals = exclusive monthly Q&A access; 10 referrals = one year paid subscription free"); your unique referral link format; any data on your subscriber base that makes the sharing ask feel meaningful (e.g. "our readers are mostly professionals who know other professionals in the same field"); a short description of the type of reader most likely to appreciate the newsletter
How the Assistant Approaches This
- Opens with the value-first framing: before the ask, gives the reader a brief reminder of why they find the newsletter worthwhile — this activates the psychological state most likely to lead to sharing
- Makes the ask specific and personal: "forward this to one colleague who..." is consistently more effective than "share with your network"; the copy names the ideal recipient to help the reader picture a real person
- If there are referral rewards, presents them simply and concretely — a table or a brief tier list, not a paragraph of programme mechanics. Avoids making the rewards sound like the primary reason to share (this backfires by making sharing feel transactional)
- Provides 2–3 lines of ready-to-copy share text that subscribers can paste into a message, email, or social post — removing the effort of composing their own recommendation is the single most effective referral conversion technique
- Closes with the referral link placeholder and a low-pressure sign-off
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 81 lines · 49 tokens per session scan A 855802275887
referral-copy-writer is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 49 tokens to every session and 1,331 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
analytics-strategy
Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement.…
cro-optimization
Run conversion rate optimization through hypothesis-driven testing including audit, hypothesis generation, test design, statistical analysis, and rollout decisions. Use this skill whenever the user wants to optimize conversion, run A/B tests, audit a funnel, generate test hypotheses, design experiments, or analyze…
newsletter
Use when running an email newsletter as a recurring publication — subject + preview pair, issues that turn opens into clicks, the welcome sequence, cadence and engagement tiering, growth loops, and a post-Apple-MPP click scorecard. NOT one-off launch or nurture sends (that is marketing), NOT SPF/DKIM/DMARC (that is…
viral-marketing-playbook
Design viral loops into your product — referral programs, invite systems, and share mechanics that drive exponential growth. Includes K-factor calculations and real examples from Dropbox, Slack, and Notion. By @WeiYipei.
xiaoyuzhou-podcast-notes
A workflow that turns a public Xiaoyuzhou FM podcast episode into structured Markdown notes and a saved transcript. Xiaoyuzhou FM is a Chinese podcast platform.
c-research
Summarize web URLs, PDFs, YouTube videos, and podcasts using the summarize CLI. Instantly extract key points from any content type without manual reading. Useful for research, link digests, and media review.