A command is the one you type. It runs exactly when you ask it to, and never before.
9,227 commands across 665 plugins.
Generate tests for a completed phase based on Evidence Review criteria and implementation
Steerable code review that challenges the design and approach, not just implementation defects. Read-only; never edits files.
Verify a page or flow in a real browser via Cursor's `chrome-devtools` MCP. Read-only — Cursor reports; does not modify source files.
Research the latest available models from Anthropic, OpenAI, and Google, then update the project's model configuration accordingly.
Extract a full task specification up front (goal, constraints, definition of done), then execute — the primary documented lever for Opus 4.8 long-horizon…
Write this session's lessons into the project's lessons/ directory using the memory-discipline format.
Spawn a fresh-context verifier subagent to check completed work against its specification before trusting it.
Critical thinking analysis - validates alignment, challenges assumptions, identifies risks
Comprehensive quality audit - code quality, documentation, coverage, security
```markdown --- status: accepted date: YYYY-MM-DD ---
**ALWAYS use these Bash commands. NEVER use mcp__claude-in-chrome__* tools.**
Identify skills injected where not needed, propose regex and description tightening
Run the fable-mode eval suite (probes → pairwise judge → report). Costs tokens — runs headless claude many times. Optional arg: a probe id substring to filter.
Report fable-mode posture — output style, model/effort, hook telemetry drift counts
Turn rolling-context off for this session (or --global for the whole machine) — full history goes upstream uncompressed, no restart needed
Turn rolling-context back on for this session (or --global for the whole machine) — active from the next request
Restart the rolling-context proxy now (e.g. to pick up a plugin update the start hook deferred because other sessions were mid-request)
Hardstop - Pre-execution safety layer for shell commands. Shows status and help.
Analyse an AML alert, identify typologies, apply the disposition decision tree, and draft a SAR if warranted.
Calculate Basel III/IV capital ratios, assess buffer compliance, and determine MDA headroom for a given jurisdiction.
Calculate IFRS 9 Expected Credit Loss for a facility or portfolio, applying jurisdiction-specific rules and scenario weighting.
Compress project memory. Archives older entries from MEMORY.md into archive.md to keep the hot layer lean. Run when memory-loop warns about file size.
Save current session work to project memory. Updates MEMORY.md with completed tasks, decisions, and discoveries from this session.
Show project memory status: file size, section counts, and whether compression is recommended.
Autonomous PR fixing loop - iterates on CI failures and review comments until green
Diagnose connection or behavior issues with the Ableton MCP server. Use when tools aren't responding, AbletonMCP doesn't show up in Live's preferences, or…
Pre-export checklist before rendering audio. Validates levels, headroom, mono compatibility, and sample rate settings. Use right before bouncing to file.
Bootstrap a fresh Ableton Live project with our preferred bus structure, return tracks, group templates, and color/labeling conventions. Use at the start of a…
Audit a Paymob webhook HMAC verification implementation for correctness and safe failure behavior.
Explain a Paymob error code, HTTP status, or error message and give the cause and fix.
Show Paymob sandbox test card and wallet credentials, optionally filtered by payment method.
Audit your content library for freshness decay, coverage gaps, and optimization opportunities
Configure brand voice, terminology, compliance guardrails, and style guide for content production
Generate a research-backed content brief with keyword data, competitor analysis, search intent, and SEO strategy
Print the gitleaks release sha256 for a version, formatted for direct paste into a GitHub Actions workflow or `agent-guard setup --install`. Pass an optional…
Run a deterministic one-shot secret scan over the repository's pending changes (staged content, unstaged worktree edits, and untracked files; gitignored paths…
Delegate a coding or investigation task to Grok (write-capable by default)
Find symbol definition(s) via cix — go-to-definition across the indexed codebase
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic