Borrowing it
Nothing to install: this file belongs to yasuflatland-lf/liferay-dummy-factory. 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/yasuflatland-lf/liferay-dummy-factory/master/.claude/skills/liferay-debug/SKILL.mdgit clone --depth 1 https://github.com/yasuflatland-lf/liferay-dummy-factoryWrote 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/yasuflatland-lf/liferay-dummy-factory/liferay-debug)<a href="https://agentmods.dev/skills/yasuflatland-lf/liferay-dummy-factory/liferay-debug"><img src="https://agentmods.dev/badge/skills/yasuflatland-lf/liferay-dummy-factory/liferay-debug/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/yasuflatland-lf/liferay-dummy-factory/liferay-debug"><img src="https://agentmods.dev/badge/skills/yasuflatland-lf/liferay-dummy-factory/liferay-debug.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 | $0.00066 | $0.00388 |
| Opus 5.5 | $0.00026 | $0.00155 |
| Sonnet 5.5 | $0.00013 | $0.00078 |
| Haiku 4.5 | $0.00007 | $0.00039 |
Grade A, and why
liferay-debug scanned grade A with 1 finding 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 20d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
4. **Inspect the live system** with the commands at the top of the troubleshooting guide: container log, GoGo shell (`lb`, `diag`, `headers`, `scr:info`), JSONWS via `curl`. What it actually says
Debug a Liferay Dummy Factory failure
- Reproduce and read the real error. Run the narrowest command (
./gradlew :integration-test:integrationTest --tests "<spec>" --info, or the unit task) and read the first failure, not the last. - Rule out stale state before theorizing. A pass or failure that makes no sense is often a kept container volume or a replayed Gradle result.
./gradlew removeDockerContainer, and for frontend-toolchain changes./gradlew :modules:liferay-dummy-factory:clean :integration-test:clean, then rerun. - Look up the symptom in
docs/guides/troubleshooting.md(bundle, container, JSONWS/auth, Playwright tables). Follow its link to the reference section for the mechanism. - Inspect the live system with the commands at the top of the troubleshooting guide: container log, GoGo shell (
lb,diag,headers,scr:info), JSONWS viacurl. - Fix the root cause. No fallbacks that hide the failure, no skipped or weakened assertions, no
setForce(true), no--no-verify. - Record new knowledge once. A new Liferay behaviour goes into
docs/reference/liferay-dxp-api.mdordocs/reference/dxp-runtime-config.md, plus one row in the troubleshooting table that links to it. Runnode scripts/check-docs.mjs.
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.
- 20d ago First seen · 14 lines · 66 tokens per session scan A 0e0ad672ddce
liferay-debug is a skill published in the GitHub repository yasuflatland-lf/liferay-dummy-factory (50 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 388 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-10.
Other skills, from other repositories
keynobi
Use for Android work that needs state kept between calls - Gradle builds with their errors and history, logcat streaming and filtering, crashes and deobfuscated stack traces, app exit reasons, launch times, debug sessions that record each install and what followed, and UI automation on the running app - through the…
use-siteation-debugbar
Inspect Magento requests through SiteationDebugBar's MCP server. Use when asked why a page is slow, what a request did, which queries or observers ran, or to explain an error on a Magento store running this module.
rr-debug-logic
Debug a logic bug (wrong output, wrong value, incorrect behavior) using rr. Sets breakpoints at the point where the bug is observable, then reverse-executes to find where the computation went wrong.
rr-debug-race
Debug a data race or concurrency bug using rr. Records the program, then uses deterministic replay with thread inspection and watchpoints to find the exact interleaving that caused the race.
rr-debug
Debug a crash or test failure using rr reverse debugging. Records a command, replays it, and works backwards from the failure to find the root cause.
rr-debug-test
Debug a failing test using rr. Records the test suite, identifies the failing subprocess, and reverse-debugs just that process to find the root cause.