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 audience-feedback-summarizergit 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/audience-feedback-summarizer)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/audience-feedback-summarizer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/audience-feedback-summarizer/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/audience-feedback-summarizer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/audience-feedback-summarizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Output Handling · line 119 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
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 | $0.00046 | $0.02273 |
| Opus 5 | $0.00023 | $0.01137 |
| Sonnet 5 | $0.00009 | $0.00455 |
| Haiku 4.5 | $0.00005 | $0.00227 |
Grade A, and why
audience-feedback-summarizer 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audience Feedback Summarizer
What This Skill Does
Takes a batch of reader comments, survey responses, or audience messages and returns a structured summary organized by theme, sentiment, and actionable takeaways — turning scattered feedback into a clear editorial brief.
When To Use This Skill
- You have accumulated reader replies, survey results, or comment threads and need to extract patterns without reading every message individually
- You are preparing for an editorial planning meeting and need a concise summary of what readers are asking for, praising, or complaining about
- You want to identify content gaps or recurring audience frustrations that could inform your next edition, episode, or series
- A survey or feedback round has closed and you need to report findings to stakeholders or collaborators
What You Need To Provide
Required: The raw feedback text — paste in the reader messages, survey responses, comment threads, or email replies (minimum 8-10 pieces of feedback for meaningful pattern extraction; maximum limited only by context window).
Optional: The specific question the feedback was responding to (e.g., "What topics should we cover next quarter?"); the publication name and focus area; any known audience demographics; whether you want the summary focused on content feedback, product/experience feedback, or both.
How the Assistant Approaches This
-
Reads all feedback and identifies recurring themes. Groups messages by topic rather than chronology. A theme must appear in at least two separate responses to be reported — isolated one-off comments are noted separately to avoid over-indexing on outliers.
-
Categorizes each theme by sentiment and urgency. For each theme, assesses whether the overall sentiment is positive (readers want more of this), negative (readers want this fixed or changed), or mixed (divided opinions). Flags any theme where the feedback suggests urgency — a problem causing unsubscribes, a request appearing with high frequency, or a complaint about a recent specific change.
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 · 135 lines · 46 tokens per session scan A 19087933c1f3
audience-feedback-summarizer is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 11d ago), licensed MIT. It adds 46 tokens to every session and 2,273 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
Malware Analysis & Sandboxing
Static and dynamic malware analysis, YARA rule generation, sandbox configuration, behavioral profiling, and malware family classification.
weekly-performance-advisor
Generate your Weekly Performance Advisor dashboard from your La Growth Machine data: a two-tab cockpit (To do + Weekly performance) that flags campaigns to fix, sorts replies by urgency, and tracks reply volume week over week. It pulls only YOUR live LGM data, scores each running campaign against baked 3-zone…
reply-draft-assistant
Handle replies to your cold outreach end to end — classify each response, draft the right answer from the full conversation, and send it through La Growth Machine after you approve. Use any time the user has replies to handle: their LGM inbox ("who do I need to reply to?"), a campaign's replies, or a pasted thread.…
campaign-challenger
Challenge an outbound campaign copy by benchmarking it against the user's existing campaigns — what worked, what didn't, what the winners do differently — and return a concrete verdict plus prioritized fixes. Use whenever the user wants to know if a campaign or sequence is good, compare a draft to past campaigns…
Bug Root Cause Analyzer
Systematically diagnoses bugs by tracing execution flow and identifying root causes vs symptoms.
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.