Worthiness Evaluator — Security agent for Claude Code
Advisory test-worthiness audit for the emergent surface.
How to install Worthiness Evaluator
Installs to ~/.claude/agents/gaia-react-gaia-worthiness-evaluator.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/gaia-react/gaia/HEAD/.claude/agents/worthiness-evaluator.md -o ~/.claude/agents/gaia-react-gaia-worthiness-evaluator.md Restart Claude Code, or start a new session, for it to be picked up.
What Worthiness Evaluator does
name: worthiness-evaluator description: 'Advisory test-worthiness audit for the emergent surface. Reads only the phase''s changed test files plus their sibling suites; judges each test on two axes (HONESTY and WORTHINESS); returns a keep/fix/delete verdict per test. Proposes only, edits no files, every delete is human-gated.' model: opus color: green
You audit the tests a phase just added or changed on the **emergent surface** (`app/components/**`, `.playwright/**`), the surface where t
Alternatives in Security
- Genblaze Maintainer — The Genblaze Maintainer — autonomous guardian of the Genblaze repo 560 ★
- Ark Security Patcher — Fix security vulnerabilities in Ark by researching CVEs, analyzing impact, proposing mitigations, implementing 419 ★
- Advisory Hunter — Phase 1 intelligence gathering agent that collects security advisories (CVE, GHSA, OSV) with adaptive time exp 125 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Ae Reviewer
Agent Engineer reviewer. Adversarial code reviewer. Judges a diff against its plan across spec fidelity, corre
Code Audit Maintainer Shell
Maintainer-only audit of framework bash and the bats suites guarding it: quoting/portability correctness, a sh
Audit Fix Agent
Applies a single verified audit finding as a code fix in one file. Runs in parallel with sibling fix agents in
Router Tooling Engineer
Writes and tests tooling code plus its unittest suites and README/docs under ~/.claude/router/ (state.sh, swit
Changelog Keeper
Maintains CHANGELOG.md following Keep a Changelog 1.1.0 + Semantic Versioning 2.0.0. Categorizes changes into
Usability Heuristics Evaluator
Use this agent when asked to evaluate a website, app, or UI for usability issues, conduct a heuristic review,
Related Skills
Leash
Jev-powered guardrail that keeps a coding agent's output quality on a short leash: judges every turn against y
Competitor Hunter
Local web app: Claude Code runs the hunt, Jev judges every competitor post, you keep the winners. Saved-post a
Orch Review
Run the orch-review native Workflow over a diff (local changes or a GitHub PR) and report blocking vs advisory