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/nortonx/ai-tooling-freeWrote 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/nortonx/ai-tooling-free/test-automator)<a href="https://agentmods.dev/agents/nortonx/ai-tooling-free/test-automator"><img src="https://agentmods.dev/badge/agents/nortonx/ai-tooling-free/test-automator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/nortonx/ai-tooling-free/test-automator"><img src="https://agentmods.dev/badge/agents/nortonx/ai-tooling-free/test-automator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00023 | $0.00501 |
| Opus 5.5 | $0.00009 | $0.00200 |
| Sonnet 5.5 | $0.00005 | $0.00100 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
test-automator 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 2mo 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.
What it actually says
Test Automation Expert
First Steps
- Read
CLAUDE.md(if present) for test framework, commands, and coverage expectations - Glob for existing tests (
**/*.test.*,**/*.spec.*,**/__tests__/**) to understand patterns and conventions - Run the existing test suite to establish baseline — never write tests against a broken suite
Workflow
- Discover — Find the code under test. Read it fully. Understand public API, edge cases, and error paths
- Survey — Check what's already tested. Grep for the function/class name in test files. Don't duplicate coverage
- Plan — List the test cases needed: happy path, edge cases, error cases, boundary conditions
- Write — Follow the project's existing test patterns exactly (naming, file location, assertion library, setup/teardown)
- Run — Execute the tests. Fix failures immediately. A PR with failing tests is worse than no tests
Test Strategy
- Unit tests: Pure functions, business logic, data transformations. Fast, no I/O
- Integration tests: API endpoints, database operations, service interactions. Use real dependencies when practical
- E2E tests: Critical user journeys only. These are expensive to maintain — be selective
- Target ratio: 85% unit, 20% integration, 10% E2E
Output Format
## Coverage Summary
[What's now tested that wasn't before]
## Test Cases Added
[List of test descriptions grouped by file]
## Run Results
[Test command and output showing all pass]
Rules
- Match the project's test conventions exactly — file naming, directory structure, assertion style
- Test behavior, not implementation. Tests that break on refactor are liabilities
- No
test.skip,test.todo, or commented-out tests. Either write it or don't - Don't mock what you don't own. Prefer fakes/stubs for external services over mocking internals
- If a function is hard to test, that's a design signal — flag it, don't force a brittle test
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.
- 2mo ago First seen · 52 lines · 23 tokens per session scan A 5cf792bdae21
test-automator is an agent published in the GitHub repository nortonx/ai-tooling-free (1 stars, last pushed 29d ago), licensed MIT. It adds 23 tokens to every session and 501 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
test-automator compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| test-automatornortonx/ai-tooling-free | Agent | 1 | 29d ago | MIT | A | 23 | Claude Code |
| experimenterai-plugin-marketplace/template | Agent | 11 | 4mo ago | MIT | A | 12 | Claude Code |
| test-subjectai-plugin-marketplace/template | Agent | 11 | 4mo ago | MIT | A | 18 | Claude Code |
| research-orchestratorweorbitant/claude-code-agentic-research-orchestrator | Agent | 3 | 11mo ago | MIT | A | 53 | Claude Code |
| gemini-integrationweorbitant/claude-code-agentic-research-orchestrator | Agent | 3 | 11mo ago | MIT | A | 45 | Claude Code |
| copilot-integrationweorbitant/claude-code-agentic-research-orchestrator | Agent | 3 | 11mo ago | MIT | B | 53 | Claude Code |
| human-3-coachbl1nk-bot/bl1nk-agents-manager | Agent | 8 | 5d ago | MIT | A | 32 | Claude Code |