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.
git clone --depth 1 https://github.com/katalon-labs/true-skillsWrote 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/rules/katalon-labs/true-skills/test-maintenance)<a href="https://agentmods.dev/rules/katalon-labs/true-skills/test-maintenance"><img src="https://agentmods.dev/badge/rules/katalon-labs/true-skills/test-maintenance.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 5.1 | $0.00131 | $0.01325 |
| Opus 5 | $0.00066 | $0.00662 |
| Sonnet 5 | $0.00026 | $0.00265 |
| Haiku 4.5 | $0.00013 | $0.00133 |
Grade A, and why
test-maintenance 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 6d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Katalon Test Maintenance
Use this skill for the maintenance stage: keep the regression suite healthy over time and feed learning back to the plan. It consumes failure/stability signals and produces repairs plus a refreshed coverage gap list.
Availability Boundary
- Available via MCP: change/impact signals (
fetch_test_stability_data,find_test_results,read_execution), and case-level repair (update_test_case,move_test_case,duplicate_test_case). - Not directly available: Self-healing tests, Time Capsule, Studio Tracer, object refactoring, and StudioAssist Agent-mode edits are Studio-desktop features. TrueTest regeneration from live journeys is a TrueTest surface. Narrate these; MCP repairs are case-level content edits, not object/script self-healing.
Maintenance Workflow
+---------------------+ +----------------------+ +----------------------+
| Detect change impact| --> | Diagnose: repair vs | --> | Repair case assets |
| stability + history | | regenerate vs retire | | update/move/dup |
+---------------------+ +----------------------+ +----------------------+
|
v
+----------------------+
| Validate + feed back |
| to plan (gap list) |
+----------------------+
Steps and tool rules
- Detect impact.
fetch_test_stability_datafor flakiness trend;find_test_results+read_executionfor what changed across recent runs. Build the list of broken / flaky / degraded cases. - Diagnose each. Decide per case:
- Repair — the case is salvageable: fix data, steps, or expected result via
update_test_case; reorganize viamove_test_case; branch a variant viaduplicate_test_case. - Regenerate — behavior changed enough that the case should be re-derived (TrueTest regeneration / re-author) -> hand to
create-test-cases; narrate the TrueTest boundary. - Retire — behavior removed: unlink/retire (prefer update/flag over unreliable
delete_test_case); get approval.
- Repair — the case is salvageable: fix data, steps, or expected result via
- Repair (MCP-legal edits only). Pass all intended updates in one
update_test_casecall. Do not claim to have self-healed locators/objects — that is Studio. - Validate. Re-run through
execute-testand confirm viafind_test_results/read_execution. - Feed back. Emit the refreshed coverage gap list to
test-planso maintenance closes the loop instead of dead-ending.
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.
- 6d ago First seen · 108 lines · 131 tokens per session scan A 8cdf0e22df7d
test-maintenance is a cursor rule published in the GitHub repository katalon-labs/true-skills (7 stars, last pushed 12d ago), licensed MIT. It adds 131 tokens to every session and 1,325 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 2026-08-31.
Other cursor rules, from other repositories
qa-engineer
Cursor rule "qa-engineer" from ulises-jeremias/agent-toolkit, covering qa engineer, responsibility, main skill domains, when invoked and delegate to skills.
e2e-runner
Cursor rule "e2e-runner" from ulises-jeremias/agent-toolkit, covering agent vs skill rule — why agent (cite clause), when to use vs holistic, caller / skills / handoff, when invoked and selector priority (most to least resilient).
11-testing-standards
General testing and validation standards.
playwright
Playwright best practices for end-to-end testing with fixtures and page objects.
vibe-test
How to use the vibe-test MCP server for browser testing.
playwright-integration-testing-cursorrules-prompt-file
Cursor rules for Playwright development with integration testing.