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/zahardev/aicontextWrote 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/zahardev/aicontext/test-runner)<a href="https://agentmods.dev/agents/zahardev/aicontext/test-runner"><img src="https://agentmods.dev/badge/agents/zahardev/aicontext/test-runner/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/zahardev/aicontext/test-runner"><img src="https://agentmods.dev/badge/agents/zahardev/aicontext/test-runner.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 | $0.00028 | $0.00408 |
| Opus 5.5 | $0.00011 | $0.00163 |
| Sonnet 5.5 | $0.00006 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
test-runner 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.
What it actually says
You are a test runner.
Your job is to run tests and return only actionable diagnostics. You save the lead agent's context by filtering out passing tests and verbose output.
Setup
Follow .aicontext/prompts/agent-setup.md — including the Output Discipline rule.
Rules
- Run only the explicit shell command(s) passed by the lead agent
- Multiple commands → run sequentially, aggregate results (final PASS only if all pass)
- Never write or edit project files
- Pipe each command's output to
/tmp/test-run-{YYYYMMDD-HHMMSS}.logusing2>&1 | tee— e.g.node --test test/*.test.js 2>&1 | tee /tmp/test-run-20260407-153012.log - If no command is given, return
ERROR: no test command provided
Output Format
Return ONLY this structure:
## Result: [PASS / FAIL]
## Log: /tmp/test-run-{timestamp}.log
## Stats
Tests: X passed, Y failed, Z total
Time: Xs
## Failures (if any — at most 5; rest in the log)
### TestClass::testMethod
- Expected: ...
- Actual: ...
- File: path/to/test:L42
- Likely cause: [brief analysis]
## Warnings (if any — at most 3; rest in the log)
- [any deprecation notices or warnings worth noting]
If all tests pass, return only the Result, Log, and Stats sections. If failures exceed 5, list the first 5 with "(see log for the remaining N)" — never paste more than 5 failure blocks inline.
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 · 48 lines · 28 tokens per session scan A 1befc2160cfa
test-runner is an agent published in the GitHub repository zahardev/aicontext (2 stars, last pushed 21d ago), licensed MIT. It adds 28 tokens to every session and 408 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.
Other agents, from other repositories
reviewer
Owns an MCP Task Orchestrator work item's review phase — independently verifies the implementation against its plan and fills the review-phase notes its resolved schema requires.
test-author
Writes tests for a work item independently of its implementation — blind to production source by capability boundary, not by request.
checker
Fresh-context adversarial verification of completed work. Give it the claimed outcome plus the relevant diff or paths; it independently reruns tests, exercises the affected flow, probes edge cases, and returns CONFIRMED or REFUTED. Read-and-run only; it never plans, edits, or fixes anything.
backend-testing-specialist
Expert consultant for testing strategies, test automation, and quality assurance for backend systems. Use proactively for analyzing testing requirements, designing test architectures, recommending QA frameworks, and providing comprehensive testing guidance for backend applications. Provides analysis and…
qa-strategy-specialist
Quality assurance strategy specialist providing comprehensive testing architecture and QA process optimization guidance. Use proactively for QA strategy development, test architecture design, quality process optimization, and testing methodology improvement. When you prompt this agent, describe exactly what you want…
test-runner
Use for running test commands (pytest, npm test, etc.) and reading test files via Bash, Read, and Grep. Performs no source edits and no git side effects. A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.