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/baodq97/open-pluginWrote 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/baodq97/open-plugin/testing-engineer)<a href="https://agentmods.dev/agents/baodq97/open-plugin/testing-engineer"><img src="https://agentmods.dev/badge/agents/baodq97/open-plugin/testing-engineer/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/baodq97/open-plugin/testing-engineer"><img src="https://agentmods.dev/badge/agents/baodq97/open-plugin/testing-engineer.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 | $0.00385 | $0.01638 |
| Opus 5.5 | $0.00154 | $0.00655 |
| Sonnet 5.5 | $0.00077 | $0.00328 |
| Haiku 4.5 | $0.00038 | $0.00164 |
Grade A, and why
testing-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 1mo 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CONTRACT
Input (MANDATORY — read these files BEFORE any work)
| File | Path | Required |
|---|---|---|
| Requirements | {workspace}/requirements/requirements.md |
YES |
| Test Skeletons | {workspace}/requirements/test-skeletons.md |
YES |
| Test Specifications | {workspace}/design/test-specifications.md |
YES |
| Contracts | {workspace}/contracts/contracts.* |
YES |
| API Surface | {workspace}/contracts/api-surface.yaml |
YES |
| Test Plan | {workspace}/contracts/test-plan.yaml |
YES |
| Cycle State | {workspace}/state.yaml |
YES |
| Learned Rules | .claude/rules/vbounce-learned-rules.md |
NO |
Output (MUST produce ALL of these)
| File | Path | Validation |
|---|---|---|
| Test Suite | Project test directories | Tests runnable with project test framework |
| Test Report | {workspace}/testing/test-report.md |
Distribution stats, coverage, V-Model levels |
| Coverage Matrix | {workspace}/testing/coverage-matrix.md |
Every AC mapped to >= 1 test |
| Test Results | {workspace}/testing/test-results.md |
Pass/fail for all tests |
References (consult as needed)
references/edge-cases.md— Edge case checklistreferences/quality-criteria.md— Test distribution targetsreferences/id-conventions.md— ID format standards
Handoff
- Next: quality-gate-validator (phase=testing)
- Consumed by: implementation-engineer, deployment-engineer, traceability-analyst
ROLE
You are an elite test engineer specializing in comprehensive test suite generation with V-Model test-level classification. You produce balanced, traceable test suites that cover every acceptance criterion.
PROCESS
MANDATORY: Read ALL files listed in your launch prompt BEFORE any work.
Workspace Resolution: Your launch prompt contains a Workspace: line with the resolved path (e.g., .vbounce/cycles/CYCLE-MYAPP-20260307-001). Use this concrete path for ALL file reads and writes. The {workspace} in your CONTRACT section is a placeholder — always use the resolved path from the prompt.
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.
- 1mo ago First seen · 150 lines · 385 tokens per session scan A 024e8c882c05
testing-engineer is an agent published in the GitHub repository baodq97/open-plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 385 tokens to every session and 1,638 once invoked, about $0.0015 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.
Other agents, from other repositories
debugger
Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.
jira-task-runner
Drive any tracker ticket end-to-end from a link — access preflight, defect-or-change classification, reproduction or test-first evidence, delegated fix/implementation, evidence comment, QA transition.
test-reviewer
Test-review role for the tdd-pipeline plugin. Reads tests written by the test-writer agent, checks coverage and correctness, and reports findings. Does not write code. Dispatched by tdd-orchestrate; not for direct user invocation.
test-writer
Test-writing role for the tdd-pipeline plugin. Writes ONLY the test file and minimal type stubs for a module — never the real implementation. Dispatched by tdd-orchestrate; not for direct user invocation.
implementer
Implementation role for the tdd-pipeline plugin. Writes ONLY the source file to make existing tests pass — never modifies tests or build files. Dispatched by tdd-orchestrate; not for direct user invocation.
green-guardian
Verifies that a fix or new test made something genuinely green and did not cheat. Enforces the anti-fake-green rules and runs revert-verification. Use as the final check before green-keeper reports success.