ContestHQ — Testing & QA agent for Claude Code
Runs a level 3-5 contest end to end inside its folder: writes RUBRIC/SPEC/PLAN/TASKS from the harness templates, runs the score loop (ContestJudge predicts plan scores for 2-3 candidates and the plan.
How to install ContestHQ
Installs to ~/.claude/agents/fmsongx2-autocontest-harness-contesthq.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/FMsongX2/Autocontest-Harness/HEAD/agents/ContestHQ.md -o ~/.claude/agents/fmsongx2-autocontest-harness-contesthq.md Restart Claude Code, or start a new session, for it to be picked up.
What ContestHQ does
name: ContestHQ description: "Runs a level 3-5 contest end to end inside its folder: writes RUBRIC/SPEC/PLAN/TASKS from the harness templates, runs the score loop (ContestJudge predicts plan scores for 2-3 candidates and the plan is improved before building, then draft and final scores, each recorded with `ach score`), gathers evidence with DomainResearcher/ArticleResearcher, decides what to reuse instead of build with OpenSourceScout whenever the deliverable includes code, a model, a servic
Alternatives in Testing & QA
- Omd Final QA — Read-only final-gate critic 465 ★
- Eval Author — Authoring role for the D365FO agent eval loop catalog 136 ★
- Test Matrix Keeper — Expand or review the verification matrix for a growing harness surface 58 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
ContestJudge
Strict contest reviewer. Stage plan predicts the score a concept/SPEC/PLAN would earn if completed as planned,
Suite Auditor
Audits an automated test suite and scores it against a rubric. Finds sleeps, duplication, missing assertions,
Osf Clean Room
Reads a feature inside a temp folder, extracts its behavior and test coverage as a source-free specification,
Create Page
Use when scaffolding a new React page. Automates page folder creation, route-level composition setup, data-loa
BDD Harness Runner
Use PROACTIVELY as fourth stage of BDD automation (after step definitions exist) and inside the outside-in red
UX Evaluator
Use this agent for read-only UX evaluation of test-runner driver artifacts (Playwright AX-tree snapshots, scre
Related Skills
Create API Governance Program
A Claude Code skill for designing API governance programs: score five dimensions from evidence, then plan exac
Audit Skills
Periodic health audit of all skills in .claude/skills/ and agents in .claude/agents/. Scores each against a 16
Rate Cv
Claude Code skill that scores and critiques CVs against a weighted engineering-leadership rubric, with ATS and