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.
npx agentmods add agents/zahardev/aicontext/test-runnergit clone --depth 1 https://github.com/zahardev/aicontextWhat 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 | $0.00028 | $0.00408 |
| Opus 5 | $0.00014 | $0.00204 |
| Sonnet 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 2d 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.
- 2d 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 4mo ago), licensed MIT. It adds 28 tokens to every session and 408 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
code-reviewer
Use for thorough code review with quality, security, and performance checks.
vc-plan-agent
PLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features//active/ only. Use after approach is decided.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.
vc-tester
Use this agent when you need to validate code quality through testing, including running unit and integration tests, analyzing test coverage, validating error handling, checking performance requirements, or verifying build processes. This agent should be called after implementing new features or making significant…
output-evaluator
Evaluate Claude Code outputs for quality before commit/action (LLM-as-a-Judge pattern).