cursorassistant

Use when running workspace tests, choosing a test command, or summarizing results before handoff to debugger.

Use when running workspace tests, choosing a test command, or summarizing results before handoff to debugger.

Use when: running pre-commit or pre-push CI-equivalent checks in any workspace — discovers workflow commands with Cursor tools, filters for local executability, scopes to staged changes, and runs checks cheapest-first.

Use when the user wants to install or customize cursorAssistant in the current project (GitHub install or configure).

Use when: running pre-commit or pre-push CI-equivalent checks in any workspace — discovers workflow commands with Cursor tools, filters for local executability, scopes to staged changes, and runs checks cheapest-first.

Use when: discovering package manifests, assessing dependency health, finding replacements, or confirming import usage before removal — discovery only; mutating installs are handled by the deps agent.

Use before proposing cursorAssistant setup, update, or repair — inspect lockfile and managed file drift.

Use when task complexity is unclear — classify as Trivial, Simple, Compound, Complex, or Blocked and recommend the minimal path before spawning subagents.

Use when: reviewing agents/*.md, skills/*/SKILL.md, or .mdc rules for contradictions, ambiguity, persona drift, cognitive load, coverage gaps, and composition conflicts before merge.

Use when: choosing the right Cursor search strategy for a workspace query, executing and refining searches, and acting on results — exact text, regex, semantic, and file-path discovery.

Use when: deciding whether to stop and ask for clarification or proceed autonomously under an Andon cord protocol.

Use when: keeping working context tight, current, actionable, and free of stale detail.

Use when: producing lean factual responses with no filler, count-based summaries, and omitted routine narration.

Use when: reporting test and validation results with pass/fail status, minimal passing output, and concise failure triage.

Use when: auditing dependency vulnerabilities with OSV.dev queries for lockfile packages and CVE triage.

Use when: scanning for credential leakage before version control or enforcing pre-commit secret hygiene.

Use when: reviewing code for OWASP Top 10:2025 security findings with severity classification and a structured output format.

Use when: producing STRIDE threat models with trust boundaries, asset identification, and feature threat classification.

Use when: running a Red-Green-Refactor cycle with one failing test, minimal implementation, and optional commit boundary on green.

Use when: structuring a test suite, separating unit from integration tests, or deciding what a test should and should not cross as a boundary.

Use when: analyzing test coverage as a diagnostic tool, identifying gaps, or evaluating assertion strength.

Use when: selecting stubs, mocks, fakes, or spies for test isolation and deterministic behavior.