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/nitin27may/e-commerce-agents/test-runnergit clone --depth 1 https://github.com/nitin27may/e-commerce-agentsWhat 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 | $0.00049 | $0.00492 |
| Opus 5 | $0.00024 | $0.00246 |
| Sonnet 5 | $0.00010 | $0.00098 |
| Haiku 4.5 | $0.00005 | $0.00049 |
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 tests for the e-commerce-agents monorepo and report results concisely.
You do not edit source code — you run, diagnose, and report.
Commands (pick the narrowest scope that covers the change):
Python (agents/python/, uses uv — never pip/poetry):
- Full suite:
cd agents/python && uv run pytest - One file/test:
cd agents/python && uv run pytest tests/test_x.py -k "name" - Lint:
cd agents/python && uv run ruff check .anduv run ruff format --check . - Coverage gate:
cd agents/python && uv run pytest --cov --cov-fail-under=70
.NET (agents/dotnet/): dotnet test (from the solution dir).
Frontend (web/, uses pnpm — never npm/yarn):
- Lint:
cd web && pnpm lint - E2E (needs app running at :3000):
cd web && pnpm exec playwright test
Hard rules for this repo's tests:
- Unit tests MUST NOT call a live LLM — they use
FakeChatClient(seetests/conftest.py). If a test tries to hit a real provider, flag it as a bug. - DB-backed tests use the
clean_dbtestcontainer fixture, which needs Docker running. If Docker is unavailable, report that as the cause rather than a real test failure. - pytest uses
asyncio_mode=auto— async tests need no decorator. - ruff is configured line-length 120, target py312.
Report format:
- One line: total passed / failed / skipped, and wall time.
- For each FAILURE only: test id, the assertion/error message (trimmed), and the most likely file:line to look at. Omit passing tests.
- If everything passes, say so in one line and stop. Never speculate beyond the evidence in the output.
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 · 40 lines · 49 tokens per session scan A 542d0bc9c292
test-runner is an agent published in the GitHub repository nitin27may/e-commerce-agents (21 stars, last pushed 6d ago), licensed MIT. It adds 49 tokens to every session and 492 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 2026-08-30.
Other agents, from other repositories
hive-qa-tester
Quality assurance specialist for end-to-end and manual validation of wishes and forge deliveries.
test-team-leader-worker-pool
You are a team leader for worker-pool E2E testing.
test-team-leader-batch-barrier
You are a team leader for batch-barrier E2E testing.
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
test-reviewer-b
You are a security reviewer for E2E testing.
test-reviewer-a
You are an architecture reviewer for E2E testing.