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 skills/techygarg/lattice/test-qualitynpx skills add techygarg/lattice --skill test-qualitygit clone --depth 1 https://github.com/techygarg/latticeWrote 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/techygarg/lattice/test-quality)<a href="https://agentmods.dev/skills/techygarg/lattice/test-quality"><img src="https://agentmods.dev/badge/skills/techygarg/lattice/test-quality.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 | $0.00145 | $0.01823 |
| Opus 5 | $0.00072 | $0.00911 |
| Sonnet 5 | $0.00029 | $0.00365 |
| Haiku 4.5 | $0.00015 | $0.00182 |
Grade A, and why
test-quality 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Quality
Config Resolution
Projects can customize this skill's standards. Resolution order:
- Read
.lattice/config.yamlin the repo root. - If found, check
paths.test_qualityfor a custom document path. - If a custom document exists at that path, read it and check its YAML frontmatter for
mode:mode: override: the custom document has full control. Use it instead of the embedded defaults. It must be complete -- treat it as the sole reference.mode: overlay(or no mode field): read the embedded./references/defaults.mdfirst, then apply the custom document on top. A custom section replaces the matching default section (matched by exact heading); new sections append after the defaults.
- If a custom path is configured but no document exists at it → tell the user which configured path is missing, then fall back to
./references/defaults.md. - If there is no config file or no
paths.test_qualitykey, read./references/defaults.md. - Language adaptation: if
paths.language_idiomsis set in the config and the document exists, read its "Testing Patterns" section and adapt §5 (Test Naming Conventions), §4 (Test Isolation Techniques), and §6 (Test Data Builders and Factories) to the language's test-framework idioms. Language idioms take precedence over the pseudocode defaults.
Self-Validation Checklist
STOP after generating each test. Verify ALL checks before continuing. Fix every failed check. If a check is ambiguous (see Ambiguity Signals), flag it -- present options and reasoning.
- AAA STRUCTURE: Are arrange, act, and assert visually separate (blank lines)? Is there any logic (if/loop/try) inside arrange or assert?
- SINGLE BEHAVIOR: Does the test verify one behavior per the loaded doc (default: one behavior per test; a name that needs "and" → split it)?
- ASSERTION QUALITY: Does it assert observable behavior rather than implementation? Is it specific enough to catch a regression?
- ISOLATION: Does the test depend on another test's output or effects? Is all mutable state created per-test?
- TEST NAME: Does the name follow the team convention per the loaded doc (default: describe the behavior, not the method)? Is the failure message clear?
- TEST DATA: Does complex arrange use builders/factories? Are magic values promoted to named constants? (Inline literals are fine for trivial tests.)
- MOCK BOUNDARIES: Are mocks placed per the loaded doc (default: only at architectural boundaries -- I/O, external services -- not between internal collaborators)?
- TEST CODE AS FIRST-CLASS: Is the test structured like production code? Shared constants at top, helpers extracted, no dead code, clear file organization?
What ships with it
1 file 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.
- 5d ago First seen · 99 lines · 145 tokens per session scan A 48eb59828bc2
test-quality is a skill published in the GitHub repository techygarg/lattice (183 stars, last pushed 6d ago), licensed MIT. It adds 145 tokens to every session and 1,823 once invoked, about $0.0007 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 skills, from other repositories
name-your-business
Generate, refine, compare, and when needed validate distinctive names for startups, AI products, developer tools, protocols, open-source projects, apps, product families, local businesses, services, companies, nonprofits, and other organizations. Use when asked to name or rename a business, brand, product, venture…
run-smoke-tests
Inspect an unfamiliar repository, interpret a broad Markdown user journey at runtime, operate the real product through its supported web, API, CLI, desktop, or mobile surface, and produce an auditable pass, fail, or blocked judgment with screenshots, logs, recordings, and a step timeline when available. Use when asked…
async-learning-teacher
Transform saved links, papers, articles, posts, videos, and reference collections into approachable AI teaching artifacts for later study. Use when a user wants to queue learning material, create a readable explanation from a source, teach a paper or post step by step, or run an interactive tutor that validates…
build-scenario-tests
Inspect an unfamiliar repository, turn a focused Markdown behavior scenario into a deterministic test in the repository's native test stack, run it, and preserve traceability between intent and code. Use when asked to add scenario tests, compile acceptance criteria or Given/When/Then Markdown into executable tests…
plan-create
Create structured implementation plans for autonomous TDD development. Use for new features, multi-file changes, or anything requiring multiple steps or tests. Triggers on aspirational openers ("let's build", "let's start building", "I want to make", "I want an app that", "help me build"), capability lists ("users…
forge
Plan, execute, and validate complex multi-step tasks with automatic retry and memory.