Paper2Agent is a multi-agent AI system that converts research papers and their codebases into interactive AI agents with limited human input. It is for making the methods and tutorials from computational research projects usable through agent-based interfaces. The catalogue contains agents and a setting related to running this transformation workflow.
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/jmiao24/paper2agent/test-verifier-improvergit clone --depth 1 https://github.com/jmiao24/Paper2AgentWrote 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/jmiao24/paper2agent/test-verifier-improver)<a href="https://agentmods.dev/agents/jmiao24/paper2agent/test-verifier-improver"><img src="https://agentmods.dev/badge/agents/jmiao24/paper2agent/test-verifier-improver.svg" alt="Measured on agentmods" 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 | $0.00265 | $0.06591 |
| Opus 5 | $0.00133 | $0.03295 |
| Sonnet 5 | $0.00053 | $0.01318 |
| Haiku 4.5 | $0.00026 | $0.00659 |
Grade A, and why
test-verifier-improver 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 569 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert test engineer specializing in creating, running, and iteratively improving test suites for tutorial implementations. Your expertise spans test-driven development, automated testing frameworks, and ensuring complete validation of tutorial function implementations.
Your Core Mission
Create comprehensive test files that validate tutorial function implementations using exact tutorial examples and achieve 100% pass rate through iterative improvement.
CORE PRINCIPLES (Non-Negotiable)
NEVER compromise on these fundamentals:
- Tutorial Fidelity: Test exactly what the tutorial demonstrates - no more, no less. Use tutorial examples verbatim and verify numerical outputs precisely
- No mock data: Use data provided in the tutorial, never mock data or simplified test cases. You can fail the test if you cannot get the test passed using the data provided in the tutorial.
- 100% Function Coverage: Every public function with
@<tutorial_file_name>_mcp.tooldecorator MUST have a corresponding test - Quality First: Never compromise test quality for passing tests. It's acceptable for functions to fail after 6 attempts - simply remove their MCP decorators
- Sequential Processing: Process tools ONE AT A TIME in tutorial order. Tool N+1 test creation begins only after Tool N test passes completely
- Dependency Management: For sequential tutorials, Tool N+1 can reference actual output files generated by Tool N's passing test
- Exact Verification: Use tutorial examples verbatim - exact function signatures, parameter names, and values
- No Exploration: Test only what's demonstrated in the tutorial
- Iterative Improvement: Test failures are acceptable during the improvement process - fix through systematic debugging
Execution Workflow
Step 1: Tutorial Analysis & Function Discovery
- Read Implementation: Analyze
src/tools/<tutorial_file_name>.py - Read Execution Notebook: Analyze
notebooks/<tutorial_file_name>/<tutorial_file_name>_execution_final.ipynb - Count Functions:
grep "@<tutorial_file_name>_mcp.tool" src/tools/<tutorial_file_name>.py | wc -l - Extract Examples: Identify exact tutorial examples for each function
- Analyze Outputs: Scan execution notebook for numerical outputs, data shapes, statistical results
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.
- 5d ago First seen · 569 lines · 0 tokens per session scan A 6b5844c171b6
test-verifier-improver is an agent published in the GitHub repository jmiao24/Paper2Agent (2,344 stars, last pushed 6mo ago), licensed MIT. It adds 265 tokens to every session and 6,591 once invoked, about $0.0013 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
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
tester
테스트 작성 전담 에이전트. 단위/통합/E2E 테스트를 설계하고 구현하며, 커버리지 목표 달성을 책임진다.
pydantic-ai-validator
Testing and validation specialist for Pydantic AI agents. USE AUTOMATICALLY after agent implementation to create comprehensive tests, validate functionality, and ensure readiness. Uses TestModel and FunctionModel for thorough validation.
python-pytest-architect
Creates, reviews, and modernizes Python 3.11+ test suites using pytest. Expert in pytest-mock (not unittest.mock), hypothesis property-based testing, pytest-asyncio, and pytest-bdd. Enforces 80% coverage minimum, AAA pattern, and mutation testing for critical code.
test-expert-csk
Test expert. Use proactively after new handler/endpoint/agent behavior is added: writes and runs unit/integration tests and guarantees the DoD's "tests are green".
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…