Coolify is a self-hosted platform for managing servers and deploying applications, databases, static sites, and other services on hardware controlled by the user. Developers and teams use it as an alternative to hosted application platforms such as Heroku, Netlify, and Vercel, while the catalogue entries help coding agents operate Coolify.
Borrowing it
Nothing to install: this file belongs to coollabsio/coolify. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/coollabsio/coolify/main/.agents/skills/testing-best-practices/SKILL.mdgit clone --depth 1 https://github.com/coollabsio/coolifyWrote 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/skills/coollabsio/coolify/testing-best-practices)<a href="https://agentmods.dev/skills/coollabsio/coolify/testing-best-practices"><img src="https://agentmods.dev/badge/skills/coollabsio/coolify/testing-best-practices/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/skills/coollabsio/coolify/testing-best-practices"><img src="https://agentmods.dev/badge/skills/coollabsio/coolify/testing-best-practices.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 | $0.00061 | $0.00916 |
| Opus 5.5 | $0.00024 | $0.00366 |
| Sonnet 5.5 | $0.00012 | $0.00183 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
testing-best-practices 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 29d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- testing-best-practices — 89% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Best Practices
This skill provides rules for designing Laravel tests. Each rule file explains what to do and why. Use search-docs for Laravel and Pest API syntax.
This project uses Pest. Follow the corresponding guidance in each rule.
Consistency First
Read nearby tests before you choose syntax and organization.
A pattern repeated throughout the project is a convention, and project conventions take precedence over this skill. Follow them and give new tests the same structure.
These rules govern the tests you write now. An existing test that follows a project convention is not defective merely because it conflicts with this skill. Do not delete or rewrite it. If the convention has drawbacks, explain them and let the user decide.
What to Test
Read this section before you write a test.
- Test observable behavior and application contracts. A test must pass after an implementation change if the behavior stays the same.
- Cover every changed decision and each applicable high-value failure mode. A decision is a branch, a validation, a calculation, or an authorization.
- Exercise declarations through behavior instead of repeating their text.
- Leave framework behavior to framework tests. Testing project configuration is not testing the framework. A constrained relationship, cast, scope, or validation rule belongs to this project.
- Keep every test that can detect a distinct defect. When two tests detect the same defect, trim the higher-layer test to one case and report the duplication. Do not delete an existing test.
- Write a feature test first. Write a unit test only for logic that does not use the framework.
- Write a browser test only for behavior in JavaScript that a feature test cannot reach. Put a browser test in
tests/Browser, and callassertNoJavaScriptErrors()in it. - Judge an architecture test by the convention it protects, not by the rules above. An
arch()test declares a rule for an entire directory, such as the parent class of every model, the classes that may use an enum, or the methods every factory declares. It intentionally checks declarations and fails when a new file breaks the convention. - Use the test tools that the project installs. Add a new test dependency, plugin, or browser only after the user asks for it.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 29d ago First seen · 59 lines · 61 tokens per session scan A ce55a473a4fa
testing-best-practices is a skill published in the GitHub repository coollabsio/coolify (65,330 stars, last pushed today), licensed Apache-2.0. It adds 61 tokens to every session and 916 once invoked, about $0.0002 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 2026-10-02.
Other skills, from other repositories
flyenv-failure-boundaries
Use when implementing or reviewing FlyEnv multi-step operations, batch actions, PID candidate filtering, cleanup, supplementary actions, or changes to throw/reject and terminal result handling.
Docker Testcontainers
Integration testing with real dependencies in throwaway Docker containers using the Testcontainers Node.js API - GenericContainer, exposed ports, wait strategies, module containers, Docker Compose environments, and reliable cleanup.
create-verification-skill
Create one skill that teaches a bot how to launch, drive, and verify a specific app or project. Use only when the user explicitly asks for a verification skill.
release-preflight
Run the release hard-precondition gate before any tag/OTA — apc release preflight runs the real tier gate (run.ts), version alignment, and prisma regen check, all read-only. green(0) releasable · staged(3) fixable preconditions · blocked(1) tier red/envblocked. No push, no write.
test-result-feedback
Close the acceptance loop for a tested change — consume the apc test TierResult, map EACH acceptance criterion to a pass/fail outcome from structured fields (never chat text), attach an evidence ref, and write it back to the task. A SUT red is a finding, never softened to green.
impact-trace
For a change point (function / type / endpoint / SQL column), enumerate its real blast radius across six dimensions with a grep citation per row, then derive the regression test scope. Every impact-table row must trace to a real search hit — never a self-asserted claim.