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 reader-response-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/reader-response-writer)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/reader-response-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/reader-response-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/reader-response-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/reader-response-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 | $0.00040 | $0.01700 |
| Opus 5 | $0.00020 | $0.00850 |
| Sonnet 5 | $0.00008 | $0.00340 |
| Haiku 4.5 | $0.00004 | $0.00170 |
Grade A, and why
reader-response-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 7d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reader Response Writer
What This Skill Does
Drafts a thoughtful, on-brand response to a reader letter, subscriber email, or audience complaint — matching the publication's voice while addressing the reader's specific concern or question.
When To Use This Skill
- A reader has written in with a question, correction, compliment, or complaint and you need to reply promptly and professionally
- You receive a high volume of reader emails and need to draft responses efficiently without sounding templated
- A reader has raised a sensitive issue — a factual error, an offensive passage, a cancellation threat — and the response needs to be carefully worded
- You want to turn a reader interaction into a relationship-building moment that increases loyalty and reduces churn
What You Need To Provide
Required: The reader's original message (full text or a close summary); the publication name and a brief description of its voice and tone (e.g., "warm and informal," "authoritative but approachable," "journalistic and direct").
Optional: The reader's name and how they should be addressed; the context of what prompted the message (which edition, article, or episode they are responding to); any factual background the response needs to account for (e.g., "the statistic they flagged was actually correct — here is the source"); the desired outcome (retain the subscriber, acknowledge and move on, invite further dialogue, issue a correction); whether the response will be private (email reply) or public (published in a letters section or read on air).
How the Assistant Approaches This
-
Reads the reader's message for both content and emotional register. Identifies what the reader is asking for (information, acknowledgment, correction, an apology) and how they are feeling (frustrated, curious, appreciative, hostile). The response must address both — answering the question while matching the emotional context.
-
Matches the publication's voice, not the reader's. If a reader writes angrily, the response does not mirror the anger — it responds in the publication's established voice. If the publication is warm and informal, the response is warm and informal even when addressing a complaint. Consistency of voice builds trust.
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.
- 7d ago First seen · 89 lines · 40 tokens per session scan A 68ce864b8f30
reader-response-writer is a skill published in the GitHub repository ur-grue/autopunk-media-skills (30 stars, last pushed 10d ago), licensed MIT. It adds 40 tokens to every session and 1,700 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
minto-pyramid
Restructures writing into Barbara Minto's Pyramid Principle — conclusion first, then grouped reasons, then evidence — and audits an existing draft's logic against Minto's rules. Use when the user is writing, or has drafted, something that asks a reader to accept a judgment or make a decision: a recommendation…
discord-expert
Expert in Discord bot development using discord.js and discord.py, slash commands, embeds, voice channels, moderation, and bot deployment. Use when the user mentions communication, community, bots, API, Discord bot, or discord.js, or when the task involves Discord Platform, Bot Development, Discord.js Bot, or…
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.
Newsletter Summary Writer
Condenses long articles, threads, or documents into concise, engaging newsletter-ready summaries.
Community Builder
Build and grow online communities with engagement strategies and growth tactics.