source-research-brief

source-research-brief is a skill for Claude Code from ur-grue/autopunk-media-skills. It costs 41 tokens per session (1,618 once invoked), scanned A, original, MIT.

A pre-interview research brief about a potential source, including their background, public views, possible biases, conflicts of interest, and questions to ask. A source is a person whose information or testimony supports a story.

In plain words
What is it for?
It is for preparing interviews, assessing a source's track record, and planning questions for expert, background, or on-record conversations.
Why use it?
Reporters may not know how reliable or independent a source is before an interview. This brings relevant public information and possible contradictions together for preparation.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the autopunk-media-skills plugin — 187 skills shipped together

Good fit It is for preparing interviews, assessing a source's track record, and planning questions for expert, background, or on-record conversations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ur-grue/autopunk-media-skills/source-research-brief
Install

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.

Any agent
npx skills add ur-grue/autopunk-media-skills --skill source-research-brief
Clone the repo
git clone --depth 1 https://github.com/ur-grue/autopunk-media-skills

Made for: Claude Code.

Or install autopunk-media-skills, the plugin that ships this one along with the rest of its 187 skills.

Wrote 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.

agentmods badge for source-research-brief

README.md
[![agentmods](https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/source-research-brief/github.svg)](https://agentmods.dev/skills/ur-grue/autopunk-media-skills/source-research-brief)
Your own site
<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/source-research-brief"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/source-research-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.

agentmods 80×15 button for source-research-brief

Your own site · 80×15
<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/source-research-brief"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/source-research-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,618 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.01618
Opus 5 $0.00020 $0.00809
Sonnet 5 $0.00008 $0.00324
Haiku 4.5 $0.00004 $0.00162

Measured 8d ago against content hash 71826672dfc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

source-research-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.

skills/magazine-journalism/investigation/source-research-brief/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source Research Brief

What This Skill Does

Produces a structured pre-interview research brief on a potential source, covering their professional background, public positions, known biases, potential conflicts of interest, and suggested lines of questioning.

When To Use This Skill

  • You have identified a potential interview subject and need to prepare before speaking with them
  • You want to understand a source's track record before deciding how much weight to give their claims
  • You are approaching a source who has been quoted in other stories and want to know their standard narrative
  • You need to identify pressure points or contradictions in a source's public record before a difficult interview

What You Need To Provide

Required: The source's name, professional title or role, and the topic of your investigation Optional: Links or summaries of previous public statements, publications, or interviews; the source's employer or institutional affiliation; any known relationship between the source and the subject of your investigation; how you plan to use their testimony (on-record, background, expert commentary)

How the Assistant Approaches This

  1. Profiles the source's professional background and relevant expertise, distinguishing between established credentials and claimed authority
  2. Reviews the source's known public positions on the investigation topic, identifying consistency or evolution over time, and flagging any previously stated views that could affect their testimony
  3. Assesses potential conflicts of interest, institutional affiliations, funding sources, or personal relationships that could bias their account — without making unsupported accusations
  4. Generates a set of targeted pre-interview questions calibrated to probe both the substance of the story and the source's reliability
  5. After the brief, provides a "Next Step" note: whether any identified conflict of interest requires editorial review before proceeding, which question should open the interview and why, and whether foia-request-writer should be run to independently verify claims this source may make

Read the full file on GitHub · 96 lines

Files

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.

Changes

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.

  1. 8d ago First seen · 96 lines · 41 tokens per session scan A 71826672dfc2

Subscribe to this mod's changes

source-research-brief is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 41 tokens to every session and 1,618 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.

Related

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.

weisi-gu/xiaoyuzhou-podcast-notes · 220 tokens

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.

daxaur/openpaw · 52 tokens

persona-research

Public persona research authority — discover, rank, and curate public sources for a person across websites, YouTube, podcasts, newsletters, LinkedIn, and social profiles while avoiding name collisions, wrong-identity contamination, and low-signal pages.

LuuOW/meridian-mcp · 51 tokens

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.

LuuOW/meridian-mcp · 45 tokens

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.

TimSimpsonJr/magpie · 69 tokens

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…

TimSimpsonJr/magpie · 108 tokens