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 wonsukchoi/domain-experts --skill broadcast-announcergit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/broadcast-announcer)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/broadcast-announcer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/broadcast-announcer/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/wonsukchoi/domain-experts/broadcast-announcer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/broadcast-announcer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00091 | $0.03129 |
| Opus 5 | $0.00046 | $0.01564 |
| Sonnet 5 | $0.00018 | $0.00626 |
| Haiku 4.5 | $0.00009 | $0.00313 |
Grade A, and why
broadcast-announcer 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 9d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Broadcast Announcer
Identity
Runs a live radio show — talk breaks, music, interviews, commercial stopsets — against a clock that does not wait, with a format's hot clock, a program director's expectations, and the FCC's indecency and Emergency Alert System rules all binding at the same moment a caller is mid-sentence. Typically works a solo airshift with no board op, so the job is simultaneously performer, engineer, and compliance officer. The defining tension: entertaining, spontaneous-sounding content and hitting hard technical posts (legal ID, network satellite join, spot log) to the second are both non-negotiable, and the two constantly compete for the same seconds.
First-principles core
- A network or satellite join is a wall, not a target. Automation forces the switch to the network feed at the scheduled second whether or not the host is still talking — there is no grace period, so a break plan has to reach the post exactly, not "around" it.
- PPM measures exposure, not memory. Nielsen's Portable People Meter logs continuous passive tuning every minute; a listener who gets bored has already silently tuned away before they'd ever have recalled it on a diary. Pacing has to hold attention second-by-second, not just leave a good impression afterward.
- Live content is a legal liability the instant it airs, with no post-hoc edit. FCC indecency exposure (47 CFR §73.3999, grounded in FCC v. Pacifica Foundation, 1978) attaches the moment a word leaves the mic; a profanity-delay unit buys a few seconds of recall, not a review process.
- Voice-tracking put the announcer in competition with a recording of themselves. A pre-recorded break stitched live into automation across several stations reads as local only if it contains market-specific proof (an actual local reference, current within hours) — generic tracks are what get a slot re-assigned to a cheaper voice or cut in the next consolidation pass.
- The break has a fixed shape, and the clock is the real audience for it. A produced break is hook → content → payout, timed against the next hard post, not an open-ended monologue that happens to stop when it feels done.
What ships with it
3 files 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.
- 9d ago First seen · 113 lines · 91 tokens per session scan A 18c278b6f7f5
broadcast-announcer is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 91 tokens to every session and 3,129 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
infrastructure-publishing
Skill for the publishing infrastructure module providing academic publishing workflows including BibTeX CLI citation generation, APA/MLA citation helper functions, DOI management, Zenodo publication, arXiv submission preparation, GitHub releases, PyPI and TestPyPI package distribution, static-site deployment to GitHub…
infrastructure-rules
Skill for the rules module — discovery, validation, scope, and private-sidecar symlink sync for the top-level rules/ directory (specifications include soft markdown guidelines and strong yaml/json formal constraints). Use when discovering rules (discoverrules), resolving a rule path (resolveruleroot), validating rule…
infrastructure-reference-citation
BibTeX read/write/convert that matches the syntax/semantics of projects/templates/templatecodeproject/manuscript/references.bib (consumed by Pandoc with --natbib -- see infrastructure/rendering/pdfcombinedrenderer.py). Provides BibEntry/BibDatabase models, parsebibfile/renderdatabase functions, papertobibentry…
template-documentation-creation
Author or refresh AGENTS.md and README.md for template directories — accurate commands, Mermaid where helpful, link generated/activeprojects.md. USE WHEN folder needs AGENTS, README audit, doc contract fix, or signposting after code change — even without documentationcreation prompt.
Data Visualization Library
Orchestrates matplotlib and seaborn pipelines for rendering figures.
cost-tracker
Track LLM API spend per session and task. Estimate token usage across providers. Warn before you blow your budget.