Hermes — Testing & QA agent for Claude Code
Evidence-grounded specification specialist for product features, engineering changes, bug fixes, reverse specs, and spec validation.
How to install Hermes
Installs to ~/.claude/agents/karnian-agent-olympus-hermes.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Karnian/agent-olympus/HEAD/agents/hermes.md -o ~/.claude/agents/karnian-agent-olympus-hermes.md Restart Claude Code, or start a new session, for it to be picked up.
What Hermes does
name: hermes model: opus description: Evidence-grounded specification specialist for product features, engineering changes, bug fixes, reverse specs, and spec validation tools: Read, Grep, Glob
You are Hermes, the boundary between human intent and executable requirements.
Modes
The caller must choose one mode. If it does not, infer the narrowest applicable mode and state the choice.
- product-feature — problem, target users, outcomes, scope, stories, and measurable acceptance
Alternatives in Testing & QA
- Gitnexus Test CI Verifier — GitNexus test and CI reviewer 45.8k ★
- Distill — Extract an Allium specification from an existing codebase 474 ★
- Reverse Feat Composer — Barreau 3c (haut) de l'escalier reverse (ADR reverse-spec-ladder) 193 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Mid Task
Executes moderately complex tasks (focused multi-file edits, contained bug fixes, small features, test writing
AI Team Qa.Agent
AI QA engineer agent (Ivy). Use when: testing features, running E2E tests, playtesting, filing bug reports, wr
Langflow MCP Tester
Use this agent when you need to test langflow-mcp functionality after implementing fixes or new features. This
Product Docs
Creates and updates process docs, templates, decision artifacts, and agent specs. TRIGGER when: (1) task adds
E2e Writer
Writes Playwright/Maestro e2e specs and classifies failing runs. Runs ONLY against the test environment; never
Live Evaluator
Phase 3 of the grounded-persona-eval method — drives one persona through a real, live interaction with the pro
Related Skills
Overnight PRs
Autonomous overnight loop — verify issues against the codebase, close stale ones, ship PRs through /ship (bug
Engineering Craft
Use when writing or changing any production code or tests — new features, bug fixes, refactors, or test author
Idd Framework
A process framework for teams building software with AI coding agents. Replaces Epics/Features/Stories with Pr