source-credibility-brief

source-credibility-brief is a skill for Claude Code from ur-grue/autopunk-media-skills. It costs 38 tokens per session (2,595 once invoked), scanned A, original, MIT.

A source assessment for checking whether a person is qualified, reliable, independent, and supported by other evidence before their claims appear in an article.

In plain words
What is it for?
Use it to review a source’s expertise, past record, possible conflicts, and the evidence needed to support their statements.
Why use it?
It helps editors judge how much weight to give a source and whether important claims need confirmation from elsewhere.

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 Use it to review a source’s expertise, past record, possible conflicts, and the evidence needed to support their statements.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/source-credibility-brief"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/source-credibility-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,595 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 $0.00038 $0.02595
Opus 5 $0.00019 $0.01298
Sonnet 5 $0.00008 $0.00519
Haiku 4.5 $0.00004 $0.00260

Measured 8d ago against content hash 28c3146a7f41, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

source-credibility-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/fact-checking/source-credibility-brief/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source Credibility Brief

What This Skill Does

Assesses the credibility of a source whose claims appear in a draft — expertise, track record, conflicts of interest, and the corroboration needed before publication.

When To Use This Skill

  • A source is making significant claims in a story and you want a systematic assessment before deciding how prominently to feature them
  • An editor has questioned the weight given to a source and you need to document why you trust (or should qualify) their testimony
  • A source is operating outside their primary area of expertise and you need to assess how much authority to give their statements
  • You are deciding whether a claim can stand on a single source or requires corroboration

What You Need To Provide

Required: The source's name, role or title, and the specific claims they are making in the article Optional: The source's employer or institutional affiliation; any known background on the source (publications, testimony, prior interviews); how the claim was communicated (on-record interview, background, leaked document, official statement); the story context

How the Assistant Approaches This

  1. Assesses the source's expertise relative to the specific claims being made — distinguishing between claimed credentials and demonstrated expertise in the relevant domain
  2. Reviews the source's track record for reliability: prior public statements, whether they have been cited accurately in other publications, and any history of retracted or corrected claims
  3. Identifies potential conflicts of interest — financial, professional, personal, or ideological — that could affect the source's account
  4. Recommends a corroboration threshold: whether the claim can be used on a single source, requires one additional corroboration, requires documentary evidence, or should not be published without independent verification
  5. Closes with a "Next Step" note: the most important corroboration step to take immediately (contact the named corroborating expert type, locate the study or document, or run statistics-fact-checker if the claims are numerical)

Read the full file on GitHub · 149 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 · 149 lines · 38 tokens per session scan A 28c3146a7f41

Subscribe to this mod's changes

source-credibility-brief is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 11d ago), licensed MIT. It adds 38 tokens to every session and 2,595 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.