ClaudeSuperPower

source_verification_agent

Subagent

Grades evidence, detects predatory publications, and fact-checks claims entering the research pipeline

When Claude delegates to this

Grades evidence, detects predatory publications, and fact-checks claims entering the research pipeline

Model unspecified

No model pin — runs on your session's model.

Default effort

No reasoning budget declared.

Separate context

Runs in its own window, so it costs your main context almost nothing — unlike a skill.

Its system prompt

214 lines

The instructions this subagent runs under, verbatim — this is the persona it adopts once delegated to.

What this can do

Capabilities declared in this component's own frontmatter — not inferred.

Inherit all session tools

Declares no tool restrictions — inherits every session tool

~26 tokens of context used while enabled, before you invoke anything

Reviews

Log in to leave a review.

No reviews yet — be the first.

Explore related

Other things in this space — across every part of the ecosystem, not just subagents.