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/HKTITAN/cursor-best-practicesWrote 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/commands/hktitan/cursor-best-practices/run-tests-and-fix)<a href="https://agentmods.dev/commands/hktitan/cursor-best-practices/run-tests-and-fix"><img src="https://agentmods.dev/badge/commands/hktitan/cursor-best-practices/run-tests-and-fix/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/commands/hktitan/cursor-best-practices/run-tests-and-fix"><img src="https://agentmods.dev/badge/commands/hktitan/cursor-best-practices/run-tests-and-fix.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 | $0.00000 | $0.00233 |
| Opus 5 | $0.00000 | $0.00117 |
| Sonnet 5 | $0.00000 | $0.00047 |
| Haiku 4.5 | $0.00000 | $0.00023 |
Grade A, and why
run-tests-and-fix 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 9d 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
Run the project's test suite, fix any failures, and report what changed.
Steps
-
Run tests
- Use the project's actual commands (e.g.
npm test,pnpm test,pytest,cargo test,go test ./...). - If the project has multiple test commands (unit vs e2e), run the relevant one(s) for the current changes.
- Use the project's actual commands (e.g.
-
If any tests fail
- Analyze the failure (assertion, error message, stack trace).
- Fix the implementation (or add missing tests for new behavior). Do not skip tests or change expectations solely to make them pass.
- Re-run tests until they all pass.
-
Summarize
- What was broken (which test(s), why).
- What you changed (files, approach).
- Confirm all tests now pass.
Rules
- Do not delete or weaken tests to get green. Fix the code.
- Apply project rules from
.cursor/rulesorAGENTS.mdwhen relevant (e.g. test style, coverage).
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.
- 9d ago First seen · 23 lines · 0 tokens per session scan A 269340994c24
run-tests-and-fix is a command published in the GitHub repository HKTITAN/cursor-best-practices (5 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 233 tokens. 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 commands, from other repositories
gauntlet-loop
Beat a real-world quality bar via builder/critic loops; critics alone decide when each part passes.
instruction-ablation
Rebuild a minimal instruction set from a bare baseline on one real task; add instructions only after repeated failures.
prompt-eval-debug
Debug any prompt with a tiny eval suite (control, edge, boundary), failure diagnosis, and smallest next change, no blind rewrite.
tdd
Canon TDD (specify, encode, fulfill) with one test at a time, approval gates, and kitchen-cleaning refactor when needed.
run-all-tests-and-fix
Run full test suite and fix failures.
write-unit-tests
Write meaningful unit tests for target code.