Plans bounded manual or exploratory observation of requested product behavior when the developer explicitly requests manual testing, exploratory testing, or an active plan slice requires it. Covers web, CLI, API, desktop, or combined surfaces. Does not run proactively or replace required automated tests.
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Use only on explicit developer request or plan-slice manual testing. No diagnosis, product repair, or unrequested tooling.
Resolve scope and time budget from the request: a feature, story set, recent deliveries, or change range. Recover current promises, examples, and constraints from this project's records or Git history, including deleted stories. Apply later decisions before older expectations; implementation, narration, and existing tests are not the oracle.
Identify in-scope externally observable surfaces, including non-web. Resolve URLs, accounts, startup, secrets, and tools from this project's guidance when needed; do not guess credentials.
If oracle, budget, or needed environment or access is missing, name it and stop; do not invent them.
A standalone session the developer accepts is a mission:
admit it before
setup or exploration, approach unselected, unless explicitly selected as
one-shot work. Observation
required by an active plan slice or story continues under that story.
Admission changes none of the testing-only limits here.
Before acting, list coverage areas and journeys, risks or questions, and proportional split of preparation, breadth, selective depth, and surprise/confirmation reserve. Weight by importance and risk. Include each promised surface. Completing this plan is not acceptance.
When a slice requires a developer-operated observation, take its question, rounds, and developer-performed steps from the slice and ask once for the set, not round by round; see plan and reuse developer-operated observation.
For a standalone session that needs a project checkout, first read and follow the shared exploration workspace lifecycle. Enter that lifecycle before checkout-bound setup and use its selected checkout throughout the session.
Choose the cheapest reliable route: existing setup, whole or partial automated journey, or temporary harness or test, including a setup-only feature scenario using existing steps. Skip setup when current state serves. Confirm state, session, and required services remain available for external observation; a finished batch run may not. Preserve isolation, cleanup, compatible-state reuse, and removal of owned temporary artifacts. Missing reuse is a possible improvement, not authority for permanent test/runner changes. If no supported route leaves a usable starting state, name it and stop.
Cover planned areas in breadth first with this project's tools. Spend depth on surprises and high-risk questions; reallocate remaining time, keeping confirmation reserve. Reuse sufficient automated evidence; do not replay deterministic checks or proven setup. If a needed tool or environment is unavailable, name it and stop.
When planned coverage completes with no actionable findings or material
uncertainty, report exactly Good. Otherwise report only discrepancies
(expected versus actual plus evidence), unresolved expectations (not false
fails), improvements (out-of-scope ideas, not failed acceptance), and
material coverage gaps. Never report Good. when blocked or incomplete.
Omit narration, speculation, and completion markers. Do not start repair,
root-cause, or permanent test changes.
On normal completion, close or retain the workspace through the shared
exploration workspace lifecycle.
It owns which workspace is removed, safe cleanup, and exact retention when
cleanup is unsafe. An admitted session, including one reporting Good., then
follows
finish the mission.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Backend Java — Spring Boot controllers/services, JUnit controller tests, MakeMe. Read this first for any backend work. Use when working on the Java Spring backend.
The English summary is being prepared. Showing the original description.
Backend Java production code, Spring Boot controllers/services/repositories, controller return values, imports, schema ERD pointer. Use when editing backend production Java.
The English summary is being prepared. Showing the original description.
Backend Java tests, controller-level stable-boundary tests, JUnit, @Nested, MakeMe builders, @Transactional, parameterized tests. Use when writing or changing backend JUnit tests.
The English summary is being prepared. Showing the original description.
related to donut CLI. Use when working on donut-cli.
The English summary is being prepared. Showing the original description.
Set up and run the Donut dev environment on Cursor Cloud VM (no Nix). Use when working on Cloud VM, running tests on Cloud VM, or encountering command errors related to missing nix. Triggers on: cloud VM, cloud agent, no nix available, /workspace path.
The English summary is being prepared. Showing the original description.
Regenerate docs/database-erd.md from MySQL information_schema (Mermaid ERD: foreign keys and key columns). Use after Flyway schema changes, new migrations, or when the diagram is stale. Triggers on: database ERD, database-erd.md, export_database_erd, schema diagram, ER diagram after migration.
The English summary is being prepared. Showing the original description.