codex-command-center

Use for executing and enforcing governance tooling (artifact generation/validation/CI policy checks), including startup declaration checks, project-index sync checks, and repository skill-policy validation.

Use for converting ambiguous requests into explicit implementation contracts via assumptions, acceptance criteria, non-goals, constraints, and scope boundaries before major execution.

Use for selecting and enforcing the right process level across skills via deterministic risk scoring, mode-based gates, critical overrides, break-glass controls, ownership, and KPI review.

Use for minimizing token usage while preserving quality, through strict context filtering, indexed history retrieval, concise reasoning formats, output budgeting, and low-overhead execution patterns.

Use for managing the lifecycle of obsolete, superseded, merged, or renamed skills and docs with clear replacement paths, migration notes, validator warnings, and removal criteria.

Use for capping process overhead by task size, limiting skill count, validation depth, artifact creation, and user-facing ceremony before other governance or documentation skills expand scope.

Use for periodically reviewing which skills are overused, underused, missing, or creating friction by examining recent governance artifacts, handoffs, instruction trackers, and task outcomes.

Use for enforcing hard limits on cached artifacts, summaries, indexes, and other compact metadata files so they stay bounded and high-signal.

Use for maintaining a rolling summary of only the last 10 conversations and refreshing matched history entries instead of appending unbounded cache.

Use for keeping repository documentation accurate and synchronized with code changes, including README requirements, cross-skill document updates, and mandatory creation/maintenance of missing core docs.

Use for continuous maintenance of repository files with emphasis on correctness, factual accuracy, freshness, consistency, and duplicate/stale file prevention.

Use for building and maintaining compact chat/session indexes (`docs/chat-history-index.md`) so long conversations can be queried precisely without re-reading broad transcript history.

Use for implementing or amending unit tests and Playwright tests when features or behavior change, ensuring updates are validated with robust, maintainable test coverage.

Use for changes that touch multiple related files, flows, or data paths and must be planned as one connected system.

Use for planning and executing code changes with strict regression controls, including risk scoring, test impact analysis, compatibility checks, release gates, and rollback readiness.

Use for designing and maintaining repository file structure for clarity, modularity, discoverability, and low-duplication across app and documentation surfaces.

Use for reordering requested steps into dependency-correct execution order, ensuring optimal and safe operations regardless of the order instructions were provided.

Use for implementing and enforcing project backup safety, including mandatory backup scripts or scheduled backups, restore verification, retention policies, and pre-change backup gates.

Use for browser or GUI automation tasks that require iterative scripts, runtime adaptation, and debugging loops (for example dynamic scraping, authenticated web flows, CAPTCHA handoffs, and headed/headless browser control).

Use for recurring backup-restore validation and disaster-recovery simulation, including restore runbooks, drill frequency, pass/fail gates, evidence capture, and remediation tracking.

Use for deterministic shell automation and setup tasks (for example environment bootstrap, service orchestration, batch file operations, and repeatable local command pipelines with explicit validation).

Use for intent-level policy compliance checks beyond snippet presence, including whether selected skills, declared gates, and execution behavior semantically match task intent and risk.

Use for any request to review, rate, score, assess, evaluate, grade, benchmark, or otherwise judge quality; applies a custom weighted scoring model with multiple checks per category, explicit evidence, and a clear final score.

Use for planning and implementing features with strong end-user orientation by identifying expected core capabilities, practical nice-to-haves, and scope-safe enhancements that improve usefulness without drifting from explicit requirements.

Use for frontend UI/UX work that should follow the Spatial Canvas paradigm: no-scrollbar viewport framing, flat root-level navigation, one-click home anchor, minimal click depth, and in-situ actions.

Use for creating or updating `user-instructions.md` in each repository to track user directives, implementation status, owners, evidence, and last-updated timestamps with a deterministic workflow.