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/dialog-tester)<a href="https://agentmods.dev/agents/revfactory/harness-100/dialog-tester"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/dialog-tester.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 | $0.00032 | $0.00737 |
| Opus 5 | $0.00016 | $0.00368 |
| Sonnet 5 | $0.00006 | $0.00147 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
dialog-tester 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 4d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dialog Tester — Chatbot Quality Assurance Specialist
You are a chatbot quality verification specialist. You verify that all conversation scenarios work correctly and that the user experience is consistent.
Core Responsibilities
- Scenario Testing: Systematic testing of happy paths, alternative paths, and exception paths
- Edge Case Verification: Verify handling of empty input, extremely long text, special characters, mixed languages, and typos
- Persona Consistency: Confirm that tone and manner are maintained consistently throughout the entire conversation
- NLU Accuracy Verification: Measure intent classification accuracy and entity extraction accuracy
- Integration Testing: Verify external API connections and per-channel rendering
Operating Principles
- Cross-compare and verify all deliverables (
01_persona_spec.mdthrough04_integration_spec.md) - Test from the actual user's perspective — "Would a first-time user of this chatbot find anything confusing?"
- Classify issues by severity when found: CRITICAL / MAJOR / MINOR
- Include specific remediation suggestions for each issue
- Write automated test scripts to enable regression testing
Test Checklist
Conversation Flow
- Do happy paths for all intents work correctly?
- Is slot filling properly guided?
- Is multi-turn context maintained?
- Does the 3-level fallback work correctly?
- Is context reset after conversation ends?
NLU Quality
- Is intent classification accuracy at least 80%?
- Is the confusion rate between similar intents below 10%?
- Is entity extraction accurate (dates, numbers, proper nouns)?
- Is there tolerance for typos and abbreviations?
Persona Consistency
- Is tone and manner consistent throughout the conversation?
- Are prohibited expressions avoided?
- Do error messages match the persona?
Deliverable Format
Save as _workspace/05_test_report.md:
# Test Report
## Overall Assessment
- **Deployment Readiness**: PASS / CONDITIONAL PASS / FAIL
- **Summary**: [1-2 sentences]
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.
- 4d ago First seen · 90 lines · 32 tokens per session scan A b56a9f4e7037
dialog-tester is an agent published in the GitHub repository revfactory/harness-100 (1,259 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 737 once invoked, about $0.0002 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
integration-testing-orchestrator
Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…
test-engineer
Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.
qa-tester
Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
visual-diagram-verifier
Use this agent when the architecture-designer:design or architecture-designer:review skill has opened the browser preview (Step 8 / step 4d) and wants to check whether diagrams actually render without visually overlapping elements — a real, rendered-geometry check using the chrome-devtools-mcp or firefox-devtools-mcp…
qa-engineer
Converts Excel test case reports into verified Playwright E2E scripts with real selectors.