Command Claude Code
Single-use break-glass for a declared grant-aware safety hook; it never overrides a settings DENY. Forms — /allow (literal, upgraded to regex only when it contains true regex metacharacters), /allow --tool (always literal, regex off), or /allow re: (explicit regex, must be anchored). Bare /allow with no argument is…
Command Claude Code
Snapshot current progress to a refs/checkpoints/ safety ref — the branch HEAD is never moved and your working branch is never pushed; the checkpoint ref itself is background-pushed (rate-limited to 1/30s per repo, without -f).
Command Claude Code
Aggressive project cleanup - normalize docs structure, archive everything, delete one-time scripts/tests. Pass --codex to enable adversarial codex consultation on cleanliness-inspector and style-inspector; default is self-review only.
Command Claude Code
Close the current dev cycle (agent infers task-id from conversation). QA evaluates Workflow Integrity bullets and returns CLOSE YES/with-disclosures. Pass --codex to enable multi-round QA-codex debate; default is QA-only single-round assessment. --force is DEPRECATED -- a no-op alias of the normal path (audit-logged…
Command Claude Code
Delegate a task to OpenAI Codex CLI (gpt-5.6-sol, xhigh reasoning) for a second opinion or parallel coding.
Command Claude Code
Commit session changes via changelog-analyst subagent.
Command Claude Code
Enhanced development workflow with BA subagent delegation, command development best practices, Three-Party Architecture, and comprehensive automation patterns.
Command Claude Code
Autonomous overnight development loop - continuously explores codebase, finds issues, fixes them, and repeats until end-time.
Command Claude Code
Orchestrated development workflow with BA subagent delegation, parallel agent execution, and iterative QA verification. Pass --codex to enable adversarial codex consultation on each subagent's draft; default is self-review only.
Command Claude Code
Allow main agent to bypass orchestrator-gate restrictions for this turn (subagent-only operations become directly allowed). Auto-clears at stop.
Command Claude Code
Merge any resolvable commit-ish into the default branch, on either a linked (registeredworktree) worktree or an inplace one (the main checkout -- see commands/dev-overnight.md's isolationkind vocabulary). On a linked worktree, the agent infers the branch from active overnight state, auto-removes the worktree, deletes…
Command Claude Code
Execute safe git pull with automatic stash management and conflict detection.
Command Claude Code
/push is the validated wrapper for normal branch publication. Note: pretool-git-privilege-guard.py is REGISTERED in settings.json (PreToolUse, Bash matcher) and enforces commit authorization — agents must hold a valid commit grant or use the auto-bulk: bridge prefix to commit. The wrapper script /.claude/hooks/push.sh…
Command Claude Code
Run the /dev workflow with the full command specification already loaded in this conversation.
Command Claude Code
Resume every quota-interrupted subagent in the current Claude Code parent session from its original transcript and agent ID; when none is recoverable, continue the invoking session's own main agent.
Command Claude Code
Update an existing spec, continue unfinished development, or write a temp session note.
Command Claude Code
Create spec files for any dev workflow (/dev, /dev-overnight, or standalone reference). Pass --codex to enable adversarial codex consultation on each spec-subagent / QA dispatch; default is self-review only.
Command Claude Code
Cancel active overnight time-lock + workflow-enforce so the session can terminate normally. User-invoked only — agents cannot self-stop.
Command Claude Code
Test validation workflow with edge case detection, systematic validation, and quality enforcement.
Skill Claude CodeCodex
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Skill Claude CodeCodex
Apply the 58-rule anti-pattern catalog (10 Color + 5 Motion + 5 Typography + 5 Spacing + 2 Glass + 5 Heuristic + 4 UX-Writing + 5 Form + 4 Interactive + 5 Nielsen + 8 AI-slop) against a Playwright page. Outputs aestheticfindings[] with category=harddefect|tasteheuristic, with the SCHEMA-ENFORCED severity hard-cap on…
Skill Claude CodeCodex
Run APCA Lc text-contrast measurement on a Playwright page in BOTH light and dark color schemes. Returns deterministic apca. findings against rule-map.json. Use during ui-specialist Phase 6 (Accessibility).
Skill Claude CodeCodex
Inject axe-core 4.10.0 into a Playwright page and run the WCAG 2.1 a/aa rule set; emit a single deterministic findings list against rule-map.json. Use during ui-specialist Phase 6 (Accessibility) before ui-contextual-heuristics.
Skill Claude CodeCodex
Aggregate aestheticfindings, automatedfindings, and alignmentmeasurements into a single 1.0-10.0 beautyscore plus 7 weighted sub-scores and a 0.0-1.0 consistencyScore. Pure calculation step — never fails. Use during ui-specialist Phase 7 (Aggregation) AFTER all other ui- skills have completed and BEFORE writing the…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: