ArcadeAI

ArcadeAI/safeword

Command Cursor

Internal fallback used only right after the shared review coordinator reports it's run out of reviewer routes. Not something a user invokes directly.

ArcadeAI/safeword

Command Cursor

Run bounded linters and formatters for changed files (project).

ArcadeAI/safeword

Command Cursor

Deep code review with web research. Use when the user says 'double check against latest', 'verify versions', or 'check security'. Adds live research on top of the automatic quality hook — confirms you're using current library versions and APIs, not stale ones.

ArcadeAI/safeword

Command Cursor

Systematic refactoring with small-step discipline. Use when user says 'refactor', 'clean up', 'restructure', 'extract', 'rename', 'simplify', or mentions code smells. Enforces one change → test → commit when the commit can stay scoped. For structural improvements, NOT style/formatting (use /lint). NOT for adding…

ArcadeAI/safeword

Command Cursor

Run a safeword retrospective on the current session on demand — mine the transcript for friction (bugs / rough edges / gaps) and submit it through the outbound safety check before filing upstream. Use when the user says "run a retro", "/retro", or wants to capture friction before the session ends.

ArcadeAI/safeword

Command Cursor

Red-teams a ticket's test scenarios for gaps — cases that would pass even though the feature is broken (project).

ArcadeAI/safeword

Command Cursor

Self-review the spec inline and earn its Tier 1 review stamp (project).

ArcadeAI/safeword

Command Cursor

Run a quick, throwaway experiment to answer one open technical question before committing to the real build. Only runs when you ask for it directly.

ArcadeAI/safeword

Command Cursor

How to write good tests — quality knowledge for any testing context.

ArcadeAI/safeword

Command Cursor

Verify ticket completion criteria — tests, build, lint, scenarios, dependency drift.

ArcadeAI/safeword

Cursor rule Cursor

USE WHEN starting feature work, running /bdd, resuming a BDD ticket, or user says 'add', 'implement', 'build', 'feature', 'resume', 'continue'. Orchestrates BDD phases.

ArcadeAI/safeword

Cursor rule Cursor

USE WHEN in BDD intake phase OR ticket has phase:intake. Guides discovery and context gathering for features.

ArcadeAI/safeword

Cursor rule Cursor

USE WHEN in BDD done phase (verify.md exists). Close the ticket — verification already happened in verify.

ArcadeAI/safeword

Cursor rule Cursor

USE WHEN in BDD plan-implementation phase. Author impl-plan.md, run figure-it-out on load-bearing choices, ADR lifecycle, review before implement.

ArcadeAI/safeword

Cursor rule Cursor

USE WHEN in BDD define-behavior or scenario-gate phase. Guides Given/When/Then scenario creation and validation.

ArcadeAI/safeword

Cursor rule Cursor

USE WHEN BDD thresholds exceeded (2+ stories, >15 scenarios, >20 tasks). Split protocol and examples.

ArcadeAI/safeword

Cursor rule Cursor

USE WHEN in BDD implement phase. RED/GREEN TDD cycle; run /refactor after GREEN.

ArcadeAI/safeword

Cursor rule Cursor

USE WHEN in BDD verify phase OR all scenarios marked [x]. Evidence gate — cross-scenario refactor, then /verify and /audit.

ArcadeAI/safeword

Cursor rule Cursor

Collaborative brainstorming and rubber-ducking — divergence-first thinking partner. Use when the user wants to explore options, weigh approaches, or think through uncertainty before committing to a direction ('brainstorm', 'rubber duck', 'help me think', 'explore options', 'what are the tradeoffs').

ArcadeAI/safeword

Cursor rule Cursor

@.safeword/SAFEWORD.md.

ArcadeAI/safeword

Cursor rule Cursor

Finds the real cause of a bug, in four steps, before you touch a fix. Use when encountering bugs, test failures, unexpected behavior, or when previous fix attempts failed. Enforces investigate-first discipline ('debug this', 'fix this error', 'test is failing', 'not working').

ArcadeAI/safeword

Cursor rule Cursor

Extract tacit knowledge through non-obvious microquestions — things only the user knows that can't be found in code, docs, or research. Use when about to guess at intent, context, or constraints, or when user says 'ask me', 'what do you need to know', 'what's missing'. Skips questions answerable by reading the…

ArcadeAI/safeword

Cursor rule Cursor

Explore and debate options with fresh documentation and research before committing. Use when facing a real decision with multiple plausible approaches — library/framework choice, architecture call, API or schema design, algorithm selection. Looks up current docs and recent research, weighs options on correctness and…

ArcadeAI/safeword

Cursor rule Cursor

Internal fallback used only right after the shared review coordinator reports it's run out of reviewer routes. Not something a user invokes directly.