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 expert-finder-briefgit 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/expert-finder-brief)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/expert-finder-brief"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/expert-finder-brief/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/expert-finder-brief"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/expert-finder-brief.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 | $0.00034 | $0.03541 |
| Opus 5 | $0.00017 | $0.01770 |
| Sonnet 5 | $0.00007 | $0.00708 |
| Haiku 4.5 | $0.00003 | $0.00354 |
Grade A, and why
expert-finder-brief 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expert Finder Brief
What This Skill Does
Generates a structured brief identifying the types of experts needed for a story, where to find them, and how to approach them credibly.
When To Use This Skill
- You are starting an investigation and need to map out what kinds of expert sources will make the story credible
- You have a story concept but don't know which professional disciplines are most relevant
- You want a systematic approach to sourcing rather than searching for names ad hoc
- You are covering a technical subject outside your beat and need a roadmap into an unfamiliar expert community
What You Need To Provide
Required: A brief description of the story or investigation topic; the type of publication and approximate audience Optional: Any experts already identified; specific angles or sub-questions the story needs to answer; geographic constraints (local vs. national vs. international sources); deadline pressure (affects how quickly sources must be found)
How the Assistant Approaches This
- Breaks the story's core questions into distinct knowledge domains — each domain points to a different category of expert
- For each knowledge domain, identifies the most credible expert types (by professional role, institutional affiliation, or credential) and flags which are more likely to be neutral versus advocacy-oriented
- Suggests specific finding strategies for each expert type: professional associations, academic departments, regulatory agency alumni networks, conference programs, court records, and public databases
- Provides a brief approach note for each expert type — how to frame the initial contact to maximize response rate
- Closes with a "Next Step" note: which domain to contact first (typically the one that will build credibility for subsequent outreach), and whether research-brief-creator should be run to expand the full reporting plan beyond expert sourcing
Output Format
Structured brief, 600–900 words. Sections: Story Questions Requiring Expert Input (bulleted), Expert Types by Domain (2–4 domains, each with expert roles + finding strategy + Platform-Specific Sourcing Tactics + approach note). Closes with a short Sourcing Risks section flagging common pitfalls for this story type. Practical, direct tone. Output ends with a "Next Step" note: which domain to contact first, the most important approach note to act on immediately, and whether research-brief-creator should be run to build the wider reporting plan.
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 · 179 lines · 34 tokens per session scan A 234a52417b74
expert-finder-brief is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 34 tokens to every session and 3,541 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.
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.
transcript-ingestion
Transcript ingestion authority — capture, normalize, and prioritize transcripts from YouTube videos, podcast pages, captions, show notes, and transcript-like page content for persona systems, RAG pipelines, and grounded synthesis.
entity-graph
Resolve entities across an investigation's documents into a Neo4j graph after a mandatory human review gate. Layer-2, operator-tier, Docker-gated -- run it to deduplicate people/orgs across the corpus, decide the "maybe" matches yourself, then write the resolved network to Neo4j for queryable analysis.
analysis-recipe
This skill should be used when the user asks to "run the analysis recipe", "run the 13-point checklist", "run the per-source investigative pass", "analyze this FOIA/audit-log source for out-of-state / immigration / pretext / mega-users / co-travel", "roll up findings across multiple sources/agencies", or "test the…
pii-sweep
This skill should be used when the user asks to "sweep PII exposure in a FOIA free-text field", "quantify how much PII a free-text reason/narrative column exposed", "run the authoritative PII tally", "count names / SSNs / A-numbers / DOBs in a reason column weighted by row count", "separate officials named for…