Better Agents is a command-line tool and set of standards for structuring, testing, evaluating, versioning, and observing AI-agent projects. It helps developers build agents with organized prompts, scenario tests, evaluation notebooks, and framework-specific guidance. Its catalogue rules guide coding assistants in applying this structure and these practices.
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/langwatch/better-agentsWrote 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/rules/langwatch/better-agents/unit-tests-todos)<a href="https://agentmods.dev/rules/langwatch/better-agents/unit-tests-todos"><img src="https://agentmods.dev/badge/rules/langwatch/better-agents/unit-tests-todos/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/rules/langwatch/better-agents/unit-tests-todos"><img src="https://agentmods.dev/badge/rules/langwatch/better-agents/unit-tests-todos.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 | $0.00007 | $0.00155 |
| Opus 5.5 | $0.00003 | $0.00062 |
| Sonnet 5.5 | $0.00001 | $0.00031 |
| Haiku 4.5 | $0.00001 | $0.00015 |
Grade A, and why
unit-tests-todos 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 1mo 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
Stack:
- Vitest
Testing rules:
-
Test are colocated as closely as possible to the code they are testing in a
__tests__directory. -
We only test if/then logic
-
A ‘when’ should indicate a describe block, and then we will out the todos.
-
Don’t test implementation details, only the public API.
-
DO NOT WRITE THE ACTUAL TESTING, ONLY THE TODOS.
-
Propose only a spec test of todos:
Example:
describe(“Todo List”, () => {
describe(“when a todo is added”, () => {
it.todo(“adds a todo”);
});
});
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.
- 1mo ago First seen · 24 lines · 7 tokens per session scan A 532d88744869
unit-tests-todos is a cursor rule published in the GitHub repository langwatch/better-agents (1,557 stars, last pushed 4mo ago), licensed MIT. It adds 7 tokens to every session and 155 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 2026-08-30.
Other cursor rules, from other repositories
testing
Vitest testing patterns for Caliber.
hatch3r-testing
Coverage thresholds, mocking strategy, property-based testing, mutation-score targets, flaky test quarantine, and snapshot test discipline.
testing
Testing rules for vitest suite.
adr-003
Architecture questions, answered from your ADRs.
api
For creating tests for the backend in bubblelab-api.
hard-negative-tester
Specialist in hard negative testing, adversarial test case design, and robustness evaluation for AI/ML retrieval and classification systems. Crafts deceptive examples that expose model blind spots, improves RAG accuracy, and validates embedding models against edge cases. Use when building RAG evaluation suites…