audit-deep
Deep audit — same as /audit but spawns more parallel subagents, runs multi-pass review, and chases exploit chains across files.
A command is the one you type. It runs exactly when you ask it to, and never before.
2,159 commands across 254 plugins.
Deep audit — same as /audit but spawns more parallel subagents, runs multi-pass review, and chases exploit chains across files.
Plan N days of binary outcomes (3 max/day), apply prompting principles, output branded HTML tracker
Interactive ritual to discover what "done" actually means for you. Run once. Produces your personal Define Done config.
5pm ritual. Check today's outcomes, log what shipped, flag what slipped, write tomorrow's 3.
Self-check the Gearbox installation and print a PASS/WARN/FAIL report
Creates a project-local copy of the Gearbox routing policy. Optional — only needed if you want to customize the policy for this repo.
List, find, or inspect Merit Aktiva sales/purchase invoices
Sync or show the company profile — this account's real chart of accounts, banks, VAT codes, and financial years
Manually delegate a boring, low-risk task to the Antigravity CLI (agy), always reviewing the result.
Analyzes a Chili Piper distribution (round-robin queue) for imbalance vs. configured weights, booking-source and day-of-week skew, and cancellation breakdown.
Analyzes Chili Piper meeting no-show patterns by trigger type, routing path, rep, or workspace to surface actionable optimization opportunities.
Audit all Chili Piper concierge routers for coverage gaps, stale rules, empty distributions, and catch-all overflow.
Apply the same change to many Linear issues at once. Dry-run by default.
Audit Linear issues for problems (missing labels, stale, duplicates, wrong state, orphaned, unactionable) and propose fixes
Run the curator — collect signals from configured signal sources and report
Save wave state to disk so an auto-compact, session crash, or laptop battery death doesn't kill the run. Run this between phases or before any long operation.
Start a new wave. Default runs the canonical v2 framework (17 phases + conditional [DR] for UI waves at 1.5 + optional [CR] gate at 3.5, max 19). Pass --demo…
Create basic admin dashboard with protected routes. Implement admin route protection with role-based access control. Create dashboard layout with sidebar…
Integrate Google Analytics 4 for comprehensive tracking. Install gtag.js script in application layout. Create analytics wrapper hooks for type-safe event…
Integrate privacy-friendly Plausible Analytics for cookieless tracking. Add Plausible script to application layout with custom domain if configured. Implement…
Keep working toward one durable, verifiable objective with status, pause, resume, complete, clear, diagnostics, soft token budget, deadline, and Stop-hook…
You are helping the user export their journal for backup or sharing.
You are helping the user view their recent journal entries.
Is the context layer still true? 0-token staleness + broken-citation audit (no LLM, CI-friendly). Add --status for the fast hash-only subset.
Tune a DeepInit run with buttons — depth, issue detection, outputs, scope, cost, and the freshness/notification settings (disable the nudge, change its…
DeepInit preflight — tools, scope, resolved config (and whether it's valid), enabled issue families, estimated cost. 0 tokens, no LLM. Offers to install the…
Update project context using the local LLM (Qwen2.5 0.5B)
Clone a website — a working behavior ARCHIVE (real code + data replayed offline; tabs, filters, transitions work), a pixel-identical editable RESTORE (real…
Judge the current UI blind (render + screenshot if possible), grep the anti-slop patterns, and run the mandatory forced-subtraction pass.
Run the full UIForge pipeline on a brief — thesis, one direction, tokens first, sourced components, budgeted composition, blind critique, forced subtraction.
Run automated tests and build checks first, then agent code review. For each bug found, propose or document a regression test.
Recommend the best model tier for the current task based on complexity, risk, and budget.
Run formatter, linter, and type checks for a file or directory. Report remediation steps.
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic