Home / Subagents / source-verifier

source-verifier

AgriciDaniel/claude-adsSubagent

Adversarial source and claim verifier for paid-media facts, thresholds, policies, APIs, benchmarks, and repository evidence. Classifies confidence without repairing claims.

ScannedSubagentSource: GitHub
10,149 stars +266 this week Updated 19d ago License MIT Context ≈47 tokens in your chat
76popular

Why this score

Stars18/35
Usage (forks)8/15
Upkeep25/25
License15/15
Owner history10/10

This repo hosts 25 subagents, so its 10,149 stars are split between them (about 406 each) for scoring.

Popularity score: 76/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

  • Fetch web pages and search
  • Read and search files

Tools listed in the file: Read, Glob, Grep, WebSearch, WebFetch

This agent can act outside your files. Read it before installing, and narrow its tools: line if it needs less.

The agent file

---
name: source-verifier
description: "Adversarial source and claim verifier for paid-media facts, thresholds, policies, APIs, benchmarks, and repository evidence. Classifies confidence without repairing claims."
maxTurns: 24
tools: Read, Glob, Grep, WebSearch, WebFetch
---

Assume every load-bearing claim may be stale, mis-scoped, or unsupported.

Check source authority, publication and retrieval dates, refresh date,
claim-to-source fit, geography, product availability, methodology, independent
corroboration where needed, quote accuracy, and redistribution rights. Classify
exactly one of `evidence_based`, `practitioner`, `contested`, or `folklore` and
mark single-source claims.

Return structured verdicts, evidence paths, contradictions, blockers, and recovery
hints. Do not silently rewrite, reconcile, or upgrade a claim.

MIT license, from AgriciDaniel/claude-ads at commit fc3908e786c3.

Security

Scanned Oct 21, 2026 at commit fc3908e786c3, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.

NameScoreStarsContextUpdated
This onesource-verifier AgriciDaniel/claude-ads · Subagent 76★ 10k≈47 in chat19d ago
verifier Yeachan-Heo/oh-my-claudecode · Subagent Both about verifier and evidence 83★ 40k≈20 in chat16d ago
short-verifier modoojunko/awesome-novel-agent · Subagent Both about verifier 60★ 830≈15 in chat1mo ago
fix-verifier 0xSteph/pentest-ai-agents · Subagent Both about verifier 64★ 2.4k≈23 in chat29d ago
checklist-verifier The01Geek/prflow · Subagent Both about verifier and claim 56★ 99≈26 in chat16d ago
final-verifier azalio/map-framework · Subagent Both about verifier and adversarial 58★ 156≈18 in chat16d ago