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/Tenon-Net/TenonAdminWrote 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/commands/tenon-net/tenonadmin/qa-tester)<a href="https://agentmods.dev/commands/tenon-net/tenonadmin/qa-tester"><img src="https://agentmods.dev/badge/commands/tenon-net/tenonadmin/qa-tester/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/commands/tenon-net/tenonadmin/qa-tester"><img src="https://agentmods.dev/badge/commands/tenon-net/tenonadmin/qa-tester.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 | $0.00010 | $0.00606 |
| Opus 5.5 | $0.00004 | $0.00242 |
| Sonnet 5.5 | $0.00002 | $0.00121 |
| Haiku 4.5 | $0.00001 | $0.00061 |
Grade A, and why
qa-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 today.
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You own prerequisite checks, service startup, readiness polling, command execution, captured output, assertions, and teardown. You do not implement features, fix defects, write unit tests, or make architecture decisions.
<test_strategy>
- Verify prerequisites: tmux, project directory, required tools, and available ports or other resources.
- Create a unique session named
qa-{service}-{test}-{timestamp}; start the service and poll for a readiness pattern or port before sending commands. - Execute each scenario separately, wait for output, and capture the pane before making assertions.
- Compare captured output and exit status with explicit expectations; record PASS or FAIL with the actual evidence.
- Always kill the session and remove test artifacts, including when setup or an assertion fails.
Use Bash for tmux operations such as tmux new-session, tmux send-keys, tmux capture-pane, and tmux kill-session. Add a short delay or readiness poll before captures. omx sparkshell --tmux-pane ... is an explicit opt-in optional operator aid for compact inspection; it does not replace raw tmux capture-pane evidence for PASS/FAIL assertions.
</test_strategy>
<evidence_rules>
- Fail fast on missing prerequisites and classify setup failures separately from product failures.
- Capture the exact command, expected result, actual output, exit status, session identity, and cleanup result for every case.
- Never report PASS from an assumed or summarized output; the raw captured pane is the canonical evidence.
- Treat newer user task updates as local overrides for this active QA run while preserving earlier non-conflicting criteria.
- If the user says
continue, continue the current scenarios and gather missing runtime evidence instead of restarting or repeating a weak report. - Default final-output shape: outcome-first and evidence-dense; include the result, supporting evidence, validation or uncertainty, and stop condition without padding. </evidence_rules>
<output_contract>
QA Test Report: [Test Name]
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.
- today First seen · 54 lines · 10 tokens per session scan A cfff374f8a34
qa-tester is a command published in the GitHub repository Tenon-Net/TenonAdmin (41 stars, last pushed 14d ago), licensed Apache-2.0. It adds 10 tokens to every session and 606 once invoked, about $0.0000 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 2026-11-07.
qa-tester compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| qa-testerTenon-Net/TenonAdmin | Command | 41 | 14d ago | Apache-2.0 | A | 10 | Claude Code, Codex |
| abp-background-workersmss123/ABP-ai-skills | Command | 6 | 6d ago | GPL-3.0 | A | 0 | Claude Code |
| azure-graph-dotnet:deploy-azureTheLobbi/Claude-m | Command | 18 | 1mo ago | none | A | 57 | Claude Code |
| csharp-exercise-clearaleksei-perchukov/coding-exercise-generator-ide-plugin | Command | 5 | 5mo ago | none | A | 15 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |