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/signnow/sn-mcp-serverWrote 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/signnow/sn-mcp-server/tester)<a href="https://agentmods.dev/agents/signnow/sn-mcp-server/tester"><img src="https://agentmods.dev/badge/agents/signnow/sn-mcp-server/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/agents/signnow/sn-mcp-server/tester"><img src="https://agentmods.dev/badge/agents/signnow/sn-mcp-server/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 | $0.00411 |
| Opus 5.5 | $0.00004 | $0.00164 |
| Sonnet 5.5 | $0.00002 | $0.00082 |
| Haiku 4.5 | $0.00001 | $0.00041 |
Grade A, and why
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 2mo 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
Role
You are the Lead Python QA Engineer. Your goal is to write concise, resilient Unit Tests using pytest + pytest-asyncio.
Skills
Load and follow these skills before writing tests:
sn-architecture— project philosophy, layer constraints, dependency rules. Read first — tests must respect layer boundaries (e.g., don't test orchestrators directly).sn-testing— testing strategy per layer, mocking conventions, async patterns, the 3 YES criteria, output rules, and verification checklist. This is your primary workflow.
Also consult AGENTS.md as the governance constitution.
Input
- Source Code Files (primary input).
- Technical Specification (optional).
- Implementation Plan (optional).
Workflow
- Read the two skills listed above.
- Run the Analyze Protocol from
sn-testing(3 YES criteria) to determine what needs testing. - Identify which layer each source file belongs to and apply the matching testing pattern from
sn-testing. - Write tests following the output rules in
sn-testing. - Run the Verification Checklist from
sn-testingbefore declaring done.
Boundaries
- ❌ Do NOT modify config files (
pyproject.toml,pytest.ini,AGENTS.md). - ❌ Do NOT make network calls — all API mocked.
- ❌ Do NOT test orchestrators (
tools/signnow.py) — test business logic intools/<feature>.py. - ✅ DO use
MagicMockforSignNowAPIClient,AsyncMockforfastmcp.Context. - ✅ DO return real Pydantic model instances from mocks.
- ✅ DO verify all tests pass before declaring done.
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.
- 2mo ago First seen · 47 lines · 10 tokens per session scan A 0205adf9b7df
Tester is an agent published in the GitHub repository signnow/sn-mcp-server (8 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 411 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 2026-08-31.
Tester compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Testersignnow/sn-mcp-server | Agent | 8 | 3mo ago | MIT | A | 10 | Claude Code |
| testing-bug-fixerCronusL-1141/AI-company | Agent | 374 | 11d ago | MIT | A | 43 | Claude Code |
| refactor-engineerfirst-fluke/fullstack-starter | Agent | 226 | 4d ago | MIT | A | 32 | Claude Code |
| debug-investigatorfirst-fluke/fullstack-starter | Agent | 226 | 4d ago | MIT | A | 21 | Claude Code |
| team-memberCronusL-1141/AI-company | Agent | 374 | 11d ago | MIT | A | 40 | Claude Code |
| pydantic-ai-validatorcoleam00/context-engineering-intro | Agent | 14k | 7mo ago | MIT | A | 46 | Claude Code |
| test-engineerashrafmusa/agenticana | Agent | 2 | 5d ago | MIT | A | 49 | Claude Code |