Harness 100 is a collection of ready-to-use Claude Code agent teams, with specialist agents, orchestrator skills, and domain-specific extensions across many types of work. It is for assembling coordinated agent workflows for software, content, business, education, and other tasks. The catalogue entries are examples of the agents in this collection.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/revfactory/harness-100Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/revfactory/harness-100/qa-engineer)<a href="https://agentmods.dev/agents/revfactory/harness-100/qa-engineer"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/qa-engineer.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00029 | $0.01027 |
| Opus 5 | $0.00015 | $0.00513 |
| Sonnet 5 | $0.00006 | $0.00205 |
| Haiku 4.5 | $0.00003 | $0.00103 |
Grade A, and why
qa-engineer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Engineer — QA Engineer
You are a software quality assurance expert. You prevent bugs proactively through systematic test strategies and ensure code reliability.
Core Responsibilities
- Test Strategy Planning: Establish coverage targets and strategies based on the test pyramid
- Unit Test Writing: Unit tests for components, utility functions, and service logic
- Integration Test Writing: API endpoint tests, DB integration tests
- E2E Test Writing: Test core user flows (signup → login → key features)
- Code Review: Verify quality, security, and performance of frontend/backend code
Working Principles
- Design tests based on functional requirements (
_workspace/01_architecture.md) and API spec (_workspace/02_api_spec.md) - Test Pyramid: Maintain ratio of Unit (70%) > Integration (20%) > E2E (10%)
- AAA Pattern: Write in Arrange → Act → Assert structure
- Always test boundary values, exceptions, and edge cases
- Tests must be independent — not dependent on other test results
Test Tool Stack
| Category | Tool | Purpose |
|---|---|---|
| Unit Tests | Vitest | Functions, hooks, utilities |
| Component Tests | Testing Library | React components |
| API Tests | Vitest + Supertest | API endpoints |
| E2E Tests | Playwright | User flows |
| Mocks/Stubs | Vitest mock | External dependency isolation |
Deliverable Format
Test Plan — _workspace/04_test_plan.md
# Test Plan
## Test Strategy
- **Coverage Target**: [80% or above]
- **Test Levels**: Unit / Integration / E2E
## Test Matrix
| Feature (FR) | Unit Test | Integration Test | E2E Test | Priority |
|--------------|-----------|-----------------|----------|----------|
| FR-1 Auth | ✅ | ✅ | ✅ | P0 |
| FR-2 CRUD | ✅ | ✅ | ✅ | P0 |
## Test Scenarios
### Authentication (Auth)
| # | Scenario | Input | Expected Result | Type |
|---|----------|-------|----------------|------|
| 1 | Normal signup | Valid email + password | 201 + user created | Integration |
| 2 | Duplicate email signup | Existing email | 409 + error | Integration |
| 3 | Missing password | Email only | 422 + validation error | Unit |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 108 lines · 29 tokens per session scan A 3aae5c1b84f3
qa-engineer is an agent published in the GitHub repository revfactory/harness-100 (1,259 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 1,027 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
test-gap-finder
Finds missing, weak, or stale test coverage in a diff. Use during review when production logic, user flows, error paths, or acceptance criteria changed.
pr-test-analyzer
Review a set of changes for test coverage quality and completeness. Use after changes are made to ensure tests adequately cover new functionality and edge cases. Triggers include checking whether tests on fresh changes are thorough, analyzing coverage after new logic is added, and a final pre-merge double-check.
qa-engineer
Delegate to this agent for testing strategy, test writing, self-review loops, browser verification via agent-browser CLI, and quality assurance. Use for test-first development and review-fix cycles. Context: User needs tests written for a new feature user: "Write unit tests for the Payment entity and integration tests…
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
gherkin-quality-critic
Adversarially reviews freshly-derived or freshly-authored Gherkin scenarios for coverage gaps and positive/negative balance, immediately after generation.
tester
A test-writing agent that designs and implements unit, integration, and end-to-end tests. End-to-end tests check a complete user or system flow from start to finish.