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/coffeecheese/easy-prd-testing/regression-testingnpx skills add CoffeeCheese/easy-prd-testing --skill regression-testinggit clone --depth 1 https://github.com/CoffeeCheese/easy-prd-testingWrote 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/coffeecheese/easy-prd-testing/regression-testing)<a href="https://agentmods.dev/skills/coffeecheese/easy-prd-testing/regression-testing"><img src="https://agentmods.dev/badge/skills/coffeecheese/easy-prd-testing/regression-testing.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 | $0.00043 | $0.00767 |
| Opus 5 | $0.00022 | $0.00383 |
| Sonnet 5 | $0.00009 | $0.00153 |
| Haiku 4.5 | $0.00004 | $0.00077 |
Grade A, and why
regression-testing 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 3d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Regression Testing
Goal
Verify fixed defects and stable high-value flows with script-first regression while keeping evidence under the owning priority directory.
Required Inputs
- Confirmed module artifact directory.
- Existing
06-缺陷记录.mdor priority-owned执行结果/Px/06-缺陷记录.md. - Regression target: defect ID, test case ID, priority, or user-confirmed scope.
- Confirmed environment address, login mode, account handling, and risk boundary.
- Runtime dependency check result, or permission to rerun
scripts/check-deps.shbefore script-first regression.
Stop Conditions
Stop and ask only for the earliest missing input when any required input is absent. Do not infer which defect or case should be regressed if the target is unclear.
Execution Order
- Read the related defect records and test cases.
- Confirm the regression target if it is ambiguous.
- Reuse the dependency check result, or rerun
scripts/check-deps.shwhen the previous result is absent or stale. - Check
执行结果/Px/regression-scripts/and执行结果/Px/scripts/for related Playwright Test scripts. - If scripts exist but Playwright is unavailable, show the suggested install command and ask for explicit user confirmation before installing.
- Run available Playwright Test scripts first when dependencies are available.
- Record pass, failure, or blocker in
执行结果/Px/07-回归记录.md. - Classify failures as product issue, script drift, environment/data blocker, dependency blocker, or unclear.
- Use
agent-browseronly when the script result is not enough to classify the failure, or when Playwright is unavailable and the user declines installation. - Escalate to Chrome DevTools CLI only when browser evidence is insufficient and the dependency check shows CLI is available.
- Escalate to Chrome DevTools MCP only when CLI diagnostics are unavailable or insufficient and MCP is configured.
- Update
执行结果/Px/08-回归缺陷状态.md.
Write Boundaries
- Write only inside the priority directory that owns the regressed case or defect.
- Do not modify
01-04planning artifacts. - Do not overwrite first-run
05-执行记录.mdor06-缺陷记录.md. - Store regression screenshots in
regression-screenshots/. - Store regression videos in
regression-videos/. - Store Playwright trace, DevTools trace, HAR files, and trace summaries in
regression-traces/. - Store regression Playwright Test scripts in
regression-scripts/.
What ships with it
2 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.
- 3d ago First seen · 63 lines · 43 tokens per session scan A 7a54b33d2cf8
regression-testing is a skill published in the GitHub repository CoffeeCheese/easy-prd-testing (2 stars, last pushed 22d ago), licensed MIT. It adds 43 tokens to every session and 767 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.
playwright-component-testing
Set up component testing with Playwright using a story gallery — scaffold stories and a gallery dev page driven by the built-in mount fixture, no dedicated component-testing runtime. Use when asked to test React or Vue components in isolation with Playwright, or to migrate off @playwright/experimental-ct-react / -vue.
playwright-test-results
Query Playwright CI test results from the aggregated DuckDB database. Answers questions about flaky tests, failure rates, slow tests, and per-run/SHA/PR results without hunting through GitHub artifacts.
playwright-trace
Inspect Playwright trace files from the command line — list actions, view requests, console, errors, snapshots and screenshots.
playwright-triage
Triage a Playwright bug report by reproducing it from the information in the issue. Use when asked to triage, reproduce, or verify a GitHub issue (a new bug report, or an existing report with a new comment).
playwright-dev
Explains how to develop Playwright - add APIs, MCP tools, CLI commands, and vendor dependencies.