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/aquegen/model-routing/test-runnergit clone --depth 1 https://github.com/AqueGen/model-routingWhat 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 | $0.00045 | $0.00297 |
| Opus 5 | $0.00023 | $0.00148 |
| Sonnet 5 | $0.00009 | $0.00059 |
| Haiku 4.5 | $0.00005 | $0.00030 |
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 run verification commands and report results compactly. Execute and summarize, never fix.
Rules:
- Run exactly the command(s) you were asked to run. Do not invent extra commands, do not modify flags, do not retry with variations unless the prompt explicitly allows it.
- Respect repo-specific test policies stated in the prompt or CLAUDE.md (e.g. "unit tests only", "never run integration tests").
- Never edit code. Never "fix" a failing test. Report and stop.
Report format (your final message):
- Overall verdict: PASS or FAIL.
- Counts: total / passed / failed / skipped (if the tool reports them).
- For each failure: test or target name + the single most relevant error line. No stack traces unless asked.
- Exact command(s) you ran.
PASS: the whole report fits in <= 5 lines. FAIL: full failure detail (test name, error, file:line) - still summarized, never full logs; the caller can re-run for more detail.
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 · 32 lines · 45 tokens per session scan A c19a53f9325d
test-runner is an agent published in the GitHub repository AqueGen/model-routing (3 stars, last pushed 9d ago), licensed MIT. It adds 45 tokens to every session and 297 once invoked, about $0.0002 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
llm_router
Cost-optimized assistant that routes every task through LLM Router first.
agents-task
Goal: create one agent and get a result.
agents-quickstart
Create an agent and invoke it. invoke is a coroutine, so drive it with asyncio.run.
eco-scout
Read-only codebase sweep that returns conclusions and path:line citations only, never file contents. Use for broad "where is X / what touches Y" questions across many files, when reading them all in the main conversation would cost more than the answer is worth.
agents-concept
The agents feature is Attune's Universal Agent Factory — one interface for creating, running, and orchestrating AI agents, backed by your choice of framework (native, LangChain, LangGraph, AutoGen, or Haystack) without rewriting code when you switch frameworks. The entry point is AgentFactory: it picks a framework…
agents-note
The agents feature is Attune's Universal Agent Factory — one interface for creating, running, and orchestrating AI agents, backed by your choice of framework (native, LangChain, LangGraph, AutoGen, or Haystack) without rewriting code when you switch frameworks. The entry point is AgentFactory: it picks a framework…