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/rollinsio/beyond-test-coverage/test-qualitynpx skills add rollinsio/beyond-test-coverage --skill test-qualitygit clone --depth 1 https://github.com/rollinsio/beyond-test-coverageWrote 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/rollinsio/beyond-test-coverage/test-quality)<a href="https://agentmods.dev/skills/rollinsio/beyond-test-coverage/test-quality"><img src="https://agentmods.dev/badge/skills/rollinsio/beyond-test-coverage/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 | $0.00216 | $0.02341 |
| Opus 5 | $0.00108 | $0.01171 |
| Sonnet 5 | $0.00043 | $0.00468 |
| Haiku 4.5 | $0.00022 | $0.00234 |
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 4d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
test-quality
Bring a target's tests up to a durable-quality bar. "Quality" means tests that fail when behavior breaks and survive when it's only refactored — the opposite of coverage-chasing suites that hit 100% yet catch nothing.
This skill encodes the result of a controlled experiment: pointing test generation at a multi-axis quality scorecard (rather than a coverage number) produced suites that beat human-written baselines on the auto-countable axes in 9 of 9 Python suites (8 of 9 with the model held fixed — the rubric, not the model, drove the gain). The two reference docs are that experiment's distilled output:
references/quality-contract.md— 10 anti-fragility rules, each with the repair.references/scorecard.md— the scoring axes, the improvement gate, the stop condition.scripts/score.py— measures the auto-countable axes for a suite in any supported language (Python/pytest, JS/TS, Go, Kotlin, Swift).
Read both reference docs before starting. They are the substance; this file is the procedure.
Core principle
Coverage is a floor, not a goal. Once the suite is at or above its starting coverage, more coverage doesn't count as improvement. What counts is moving the quality axes: fewer fragility patterns, more rigor signals, less real mocking, better LOC efficiency — with every test traceable to a user-observable contract.
Inputs
- Target (required): a module/package to test, an existing test file/dir to improve, or both. If the user didn't specify, ask what to target.
- Test command (auto-detect, confirm if unsure): how to run the suite with
coverage. Detect from the project's config/manifest, then by stack:
- pytest:
python -m pytest <tests> --cov=<src> --cov-branch - Jest:
npx jest --coverage· Vitest:npx vitest run --coverage - Mocha:
npx c8 --check-coverage mocha(c8/nyc for coverage) - Go:
go test -cover -coverprofile=cover.out ./... && go tool cover -func=cover.out - Kotlin:
./gradlew test(coverage via the JaCoCo/Kover plugin if configured) - Swift:
swift test --enable-code-coverage(SwiftPM) orxcodebuild test(Xcode) Readpyproject.toml/pytest.ini,package.json(scripts.test, jest/vitest config),go.mod,build.gradle(.kts)/settings.gradle,Package.swift,Makefileto find the project's real command — prefer it over the defaults above.
- pytest:
What ships with it
5 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.
- 4d ago First seen · 166 lines · 216 tokens per session scan A 0e0e954b543e
test-quality is a skill published in the GitHub repository rollinsio/beyond-test-coverage (52 stars, last pushed 2mo ago), licensed MIT. It adds 216 tokens to every session and 2,341 once invoked, about $0.0011 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
ceo-setup
One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.
developer-setup
One-time onboarding for the developer workflow — installs github-workflow missions, creates the commitments workspace, registers per-repo projects, writes calibration memories. After successful setup this skill is excluded from selection until the marker file is deleted.
portfolio
Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction. Activates when the user pastes a wallet address or asks about yield/positions/rebalancing. Bootstraps a per-user "portfolio" project, aggregates positions across all the user's addresses inside one project, and offers a…
commitment-setup
One-time setup for the commitments tracking system. Creates workspace structure, schema docs, and installs triage and digest missions. Excluded from activation once projects/commitments/README.md exists in the workspace (the file this skill writes as its first step).
content-creator-setup
One-time onboarding for the content creator workflow — content pipeline stages, trend expiration, cross-platform cascades, heavy idea parking. After successful setup this skill is excluded from selection until the marker file is deleted.
parallel-pr-review
Use when asked to "review the open PRs", review a batch or stack of pull requests, or run a recurring PR-review pass on a repo — especially with many PRs, stacked branches, conflicts, or security-sensitive changes. Covers grouping, fan-out to review subagents, verdict synthesis, and posting.