source-scorer

source-scorer is a skill for Claude Code, Codex from JansenAnalytics/claudex. It costs 46 tokens per session (724 once invoked), scanned A, original, MIT.

A tool that rates how trustworthy a web source is by examining its domain, content signals, and support for a specific claim. It can evaluate one URL or a batch of URLs.

In plain words
What is it for?
Use it to compare sources, validate research claims, and attach credibility scores to findings that include URLs.
Why use it?
It helps separate well-supported sources from sources that need checking, so research findings are less likely to rely on weak evidence.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to compare sources, validate research claims, and attach credibility scores to findings that include URLs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jansenanalytics/claudex/source-scorer
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 JansenAnalytics/claudex --skill source-scorer
Clone the repo
git clone --depth 1 https://github.com/JansenAnalytics/claudex

Made for: Claude Code, Codex.

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-scorer

README.md
[![agentmods](https://agentmods.dev/badge/skills/jansenanalytics/claudex/source-scorer.svg)](https://agentmods.dev/skills/jansenanalytics/claudex/source-scorer)
Your own site
<a href="https://agentmods.dev/skills/jansenanalytics/claudex/source-scorer"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/source-scorer.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 724 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.
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 $0.00046 $0.00724
Opus 5 $0.00023 $0.00362
Sonnet 5 $0.00009 $0.00145
Haiku 4.5 $0.00005 $0.00072

Measured 4d ago against content hash fd62869d86ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

source-scorer 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 4d 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/source-scorer/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source Credibility Scorer Skill

Use when: evaluating whether a source is trustworthy, comparing multiple sources, or when research-reporter findings need credibility validation.

Score a single source

node ${SOURCE_SCORER_HOME:-$HOME/projects/source-scorer}/score.cjs --url "https://..." [--content "text"] [--claim "specific claim"]

Score with JSON output (for piping)

node ${SOURCE_SCORER_HOME:-$HOME/projects/source-scorer}/score.cjs --url "https://..." --json

Score multiple URLs

echo -e "https://url1\nhttps://url2" > /tmp/urls.txt
node ${SOURCE_SCORER_HOME:-$HOME/projects/source-scorer}/score-batch.cjs --urls-file /tmp/urls.txt

Check domain tier

node ${SOURCE_SCORER_HOME:-$HOME/projects/source-scorer}/domain-tier.cjs example.com

Auto-integration

research-reporter's add-finding.cjs auto-scores when --url is provided. The credibility score is saved with the finding and confidence is averaged with the user-provided value.

Score interpretation

80–100  🟢 High credibility    — use with confidence
55–79   🟡 Moderate            — use, but cross-reference
30–54   🟠 Low credibility     — flag as unverified
0–29    🔴 Unreliable          — avoid or explicitly mark as speculation

Scoring model (0–100 total)

Factor Max Notes
Domain tier 35 docs.*/gov/edu=35, major tech=28, pubs=20, Q&A=12
HTTPS 10 URL starts with https://
Content depth 15 Word count + citation/reference patterns
Cross-reference 20 Claim found in knowledge base from other docs
Consistency 20 Default 20 (reserved for research-reporter)

Key signals that boost score

  • docs.* subdomains, .gov, .edu: highest tier (Tier 1, 35pts)
  • HTTPS: required for any real trust (+10pts)
  • Long content with references: shows substantive work (+up to 15pts)
  • Claim appears in knowledge base from other sources: strong confirmation (+20pts)

Read the full file on GitHub · 75 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. 4d ago First seen · 75 lines · 46 tokens per session scan A fd62869d86ac

Subscribe to this mod's changes

source-scorer is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 724 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 2026-09-03.

Related

Other skills, from other repositories

verification-gates

Creates explicit validation checkpoints (verification gates) between project phases to catch errors early and ensure quality before proceeding. Use when the user asks about quality gates, milestone checks, phase transitions, approval steps, go/no-go decision points, or preventing cascading errors across a multi-step…

rohitg00/skillkit · 94 tokens

Workspine

Disciplined repo-native workflow for AI-assisted development. Spec first, then build, then verify.

PatrickSys/workspine · 24 tokens

verification-loop

Evidence-before-assertions workflow. Use before claiming work is done, before release, and after any behavior change in scripts/skills/MCP.

rexleimo/aios · 32 tokens

dos-verify-done-claims

Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's dos verify and dos commit-audit — never the agent's own narration.

anthony-chaudhary/dos-kernel · 61 tokens

debug-hub

Evidence-first debugging WITH MCP tools. Use when debughub MCP server is available. Inject log calls, collect via HTTP API (port 39200), analyze through MCP tools, clean up when done. If debughub MCP is unavailable, use debug skill (bundled Python collector) instead.

rexleimo/aios · 66 tokens

source-credibility-brief

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

ur-grue/autopunk-media-skills · 38 tokens