ocx

Use when a diff or PR is too big to review by eye and the question is "what should I actually look at" — sorts each changed line into wire / CLI / API / logic / test / doc tiers, then opens a clickable local page with the real hunks. A reading order, never a verdict.

Use to implement a plan artifact from `/swarm-plan`, or a free-text implementation task with contract-first TDD + Review-Fix Loop. Tier (`low | auto | high | max`) scales builder model, loop rounds, review breadth, and Codex code-diff gate.

Use for branch, PR, or diff review before landing on main. Tier (`low | auto | high | max`) scales breadth from single reviewer to adversarial panel with architect + SOTA-gap + Codex cross-model gate. Triggers: "review", "/swarm-review", pre-merge checks.

Use when the user says "commit", "/commit", "save progress", or asks to land working changes on a feature or worktree branch. OCX working-phase posture — minimises commit count, can amend rolling Checkpoints, offers a one-time PR prompt. For pre-merge cleanup, use `/finalize`.

Use for feature planning, task decomposition, multi-perspective research, or ADR scaffolding. Tier (`low | auto | high | max`) scales research depth, architect model, and review breadth. Canonical research primitive for AI config / ADR work.

Use when the user says "codex review", "/codex-adversary", "adversarial review", "cross-model review", or asks for a different-model second opinion on a diff or plan artifact. Complements `/swarm-review` via Codex-CLI. Scopes: code-diff (default), plan-artifact (gate for `/swarm-plan`).

Use when auditing the freshness of `.claude/rules/subsystem-*.md` files against current codebase state, or when a subsystem has undergone significant change.

Use when task involve design spec, ADR, one-way-door decision, or evaluate trade-offs between architectural approaches. Invoke before implementation when requirements span subsystems or decision hard reverse. Trigger: /architect.

Use when the user says "finalize", "/finalize", "prepare this branch for main", "clean up history", "squash the branch", or landing a branch on `main`. Rewrites Checkpoint working-phase commits into clean Conventional Commits before fast-forward merge. Flags: `--squash-all`, `--dry-run`.

Use when user asks "what's next" or "next step". Prints next slash command from current state via a sonnet subagent. Flags: `--clear`, `--list`.

Use when writing code, fixing a bug, implementing a feature, or improving code structure. Invoked for typed implementation work inside `crates/`, `test/`, `website/`, or other source surfaces.

Use for code review, quality audits, SOLID/DRY consistency checks, pattern audits across the codebase, or verifying anti-pattern compliance across a scope.

Use when adding a crate, updating dependency versions, auditing licenses, scanning for vulnerabilities, or editing `Cargo.toml` / `deny.toml` / `.licenserc.toml` in the OCX project.

Use when authoring or editing OCX documentation — user guide, reference pages, website content under `website/src/docs/`, VitePress pages, or doc narrative structure.

Use when creating or editing skills, rules, agents, or hooks under `.claude/`. Also when AI knowledge has drifted from project patterns, a new Claude Code feature lands, or syncing artifacts to current state. Modes: `create`, `audit`, `refresh`, `review`, `research <topic>`.

Use when syncing website roadmap page against current GitHub issues and PRs. Matches open/closed issues + open/merged PRs to roadmap features, updates statuses, adds links, flags unlinked issues as candidates. Triggers: "sync roadmap", "/ocx-sync-roadmap".

Use when designing test suites, writing acceptance tests, validating an implementation against a spec, or planning test coverage before implementation. Trigger: /qa-engineer.

Use for security audits, threat modelling, vulnerability assessment, or evaluating the attack surface of a new capability before merge. Trigger: /security-auditor.