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 research-brief-creatorgit 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/research-brief-creator)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/research-brief-creator"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/research-brief-creator/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/research-brief-creator"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/research-brief-creator.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 | $0.00045 | $0.02121 |
| Opus 5 | $0.00023 | $0.01060 |
| Sonnet 5 | $0.00009 | $0.00424 |
| Haiku 4.5 | $0.00005 | $0.00212 |
Grade A, and why
research-brief-creator 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Brief Creator
What This Skill Does
Produces a structured research brief for a reporter starting a new story assignment — covering the key questions to answer, the types of sources to seek, documents to obtain, and potential story angles to investigate.
When To Use This Skill
- An editor has assigned you a story and you need to organize your reporting approach before you start making calls
- You're researching an unfamiliar topic and want a structured entry point before diving into background reading
- You're handing an assignment to a researcher or junior reporter and want to give them a clear brief rather than a vague direction
- You're pitching a story and want to show an editor you've thought through the reporting methodology
What You Need To Provide
Required: The story topic or assignment in one or two sentences; the publication type (news, magazine feature, investigative, business press, general interest); any known constraints (time available for reporting, word count, known deadline pressure). Optional: What you already know about the topic; any obvious angles the editor mentioned; similar stories you've read on the topic (to understand what's been covered); geographic or demographic focus; any specific sources you've already identified.
How the Assistant Approaches This
- Maps the story territory: what is established (the background a reporter should understand), what is contested (the questions still being debated by sources and institutions), and what is unknown (the gaps that could make this story original).
- Generates three distinct potential story angles — each with a different primary question, target source set, and expected evidence type. One angle is the most obvious interpretation of the assignment; the others offer alternatives that may be more original or more reportable.
- Produces a structured reporting checklist: primary sources to seek (with a brief note on why each matters), documents to request or locate, background reading, and questions for each source type. Ordered by priority — what to do first.
- Closes with a "Next Step" note: the single first action to take before any other reporting work (typically reading the original study, finding the affected individual, or filing the document request that opens other doors)
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 · 131 lines · 45 tokens per session scan A da2b3ff05b3a
research-brief-creator is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 45 tokens to every session and 2,121 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
research-reporter
Turns a feedback-synthesizer output into a stakeholder-ready report — exec summary, methodology, benchmark comparison, and prioritized recommendations — formatted for the audience reading it. Internal/quick audiences get a markdown or Notion-ready doc; formal/external stakeholders get a Word document. Routes UI-facing…
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.
food-chain-ideation
10-minute pre-ship stress-test. Run this before you ship, not instead of shipping. Dynamically selects animal agents from a behavioral DNA library matched to the specific problem, each attacking under strict role-lock with zero shared context. Weakest eliminated each round, survivor absorbs the insight and evolves…
food-chain-pitch
Investor pitch stress-tester. Spawns adversarial agents from a pitch-specific behavioral DNA library. Each attacks the pitch narrative, financial model, or due diligence surface under strict role-lock. Elimination rounds harden the pitch. Works in Claude.ai, Claude Code, Cursor, Windsurf, Copilot with no dependencies.
food-chain-code
Adversarial architecture stress-tester. Selects attacker agents from a code-specific behavioral DNA library matched to the technical decision. Each attacks under strict role-lock. Weakest eliminated, survivor absorbs and evolves. Tests architecture decisions before a line of code is written. Works in Claude.ai, Claude…
apex-to-action
Converts food chain battle output into a 90-day execution plan. Takes the Evolved Idea, Unfair Advantage Statement, and Battle Log from any food chain battle and produces what to build first, what to validate before building, what to never build, and weekly milestones. The natural next step after any food chain…