Step Coding — Testing & QA agent for Claude Code
Step agent that implements code from the plan using TDD, runs pytest/mypy/ruff, and self-corrects up to 5 times per validation type.
How to install Step Coding
Installs to ~/.claude/agents/danielstewart77-hivemind-plugin-step-coding.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/danielstewart77/hivemind-plugin/HEAD/agents/step-coding.md -o ~/.claude/agents/danielstewart77-hivemind-plugin-step-coding.md Restart Claude Code, or start a new session, for it to be picked up.
What Step Coding does
name: step-coding description: "Step agent that implements code from the plan using TDD, runs pytest/mypy/ruff, and self-corrects up to 5 times per validation type. Use in pipelines after planning." tools: Read, Write, Edit, Glob, Grep, Bash model: opus maxTurns: 75
Step: Coding
You are a step-agent in a pipeline. Implement the story using TDD and ensure all validations pass.
Configuration
- MAX_RETRIES: 5 per validation type
- Error tracking files (inside documents path
Alternatives in Testing & QA
- Facet Coder — Generates ONE facet Cypress spec (properties propertiesFx styles stylesFx events csa inspector variants) for a 41k ★
- Track Spec — Track ID: {{TRACK_ID}} Type: {{TRACK_TYPE}} (feature bug chore refactor) Priority 31.9k ★
- Witness — Independently witness that an Allium loop's convergence claim is true and was reached honestly 474 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Standards Checker
Python standards gate — runs ruff, mypy, and pytest/tox, verifies PEP 8 and typing, and writes the standards r
Deceptive Test Hunter
Audits test changes for deceptive or redundant tests. Use after writing or changing any _test.py file. Reports
Evolve Build Planner
Build-planning agent for the Evolve Loop. Externalizes Builder's internal chain-of-thought design step into an
CI Engineer
Use for continuous-integration work in this monorepo: authoring and maintaining GitHub Actions CI workflows un
QA Pipeline Expert
Runs tests, fixes failing CI pipelines, resolves lint and quality-gate failures, and sets up testing framework
Yalla Lead
Orchestrates the Yalla Coding Team across all phases — planning, build/test separation, review, and shipping.
Related Skills
Run Checks
Run all three quality gates (ruff, mypy, pytest) and print a single-screen pass/fail summary. Use before commi
TDD Check
Run the full pre-commit verification suite — pytest, ruff, mkdocs build
Runtests
Run the project's automated checks (TypeScript, mypy, pytest if scoped) and summarise failures.