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 beat-setup-guidegit 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/beat-setup-guide)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/beat-setup-guide"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/beat-setup-guide/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/beat-setup-guide"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/beat-setup-guide.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 | $0.00043 | $0.13872 |
| Opus 5 | $0.00022 | $0.06936 |
| Sonnet 5 | $0.00009 | $0.02774 |
| Haiku 4.5 | $0.00004 | $0.01387 |
Grade A, and why
beat-setup-guide 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 — 451 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Beat Setup Guide
What This Skill Does
Generates a structured setup guide for a journalist taking over or launching a new beat — covering the source map, document inventory, recurring calendar, key contacts, institutional landscape, story seeds, and a 30-day ramp-up plan.
When To Use This Skill
- You are taking over a beat from a departing reporter and received no handover notes
- You are launching a new beat that your newsroom has never staffed before
- You are moving from one publication to another and need to rebuild your source network from scratch in a new geography or subject area
- An editor has asked you to scope a beat before the newsroom commits to staffing it
- You are a freelancer developing a specialty area and need a systematic approach to building coverage infrastructure
What You Need To Provide
Required: The beat description (subject area and scope); geographic scope (city, region, state, national); publication type and audience (daily newspaper, alt-weekly, trade publication, digital-first, magazine); any known major institutions, agencies, or organizations the beat covers Optional: How many institutions or jurisdictions fall within the beat; whether a predecessor held the beat and what (if anything) was handed over; your existing familiarity with the subject area; known upcoming events or deadlines in the first 90 days; any specific editorial priorities your editor has flagged; the size of the newsroom (affects how much you can delegate)
How the Assistant Approaches This
- Maps the institutional landscape first: who holds power, who holds information, and where the two overlap. Identifies the formal decision-making structure (elected officials, boards, appointed administrators) and the informal power structure (lobbyists, major donors, union leaders, community organizers, longtime staff who outlast their bosses). For each institution on the beat, traces the governance chain — who appoints whom, who controls the budget, who sets the agenda — and notes where formal authority diverges from actual influence.
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 · 451 lines · 43 tokens per session scan A 09e058d747eb
beat-setup-guide is a skill published in the GitHub repository ur-grue/autopunk-media-skills (30 stars, last pushed 10d ago), licensed MIT. It adds 43 tokens to every session and 13,872 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
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.
SDK Quickstart Writer
Generates a concise, copy-paste-ready quickstart guide for any SDK or library.
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.
mk:help
Workflow navigation assistant. Scans project state (plans, reviews, tests, git) and recommends the next step in the 7-phase pipeline. Use when asked "what should I do next?", "where am I?", "help", or at session start. NOT for domain complexity routing (see mk:scale-routing); NOT for skill discovery (descriptions…
Hiring Review
Use when reviewing an employment offer letter (and any restrictive-covenant exhibits) against the candidate's actual work jurisdiction and the employer's standard hiring practices to produce a structured draft review memo with a verdict, for attorney review.
KYC Onboarding Review
Use when reviewing a client or investor onboarding packet to inventory documents, extract KYC fields, apply the firm's KYC/AML rules grid, propose a customer risk rating, and assemble an escalation packet for compliance and attorney review.