sergei-aronsen/claude-code-toolkit

sergei-aronsen/claude-code-toolkit

Command

Remove an entry from .claude/rules/audit-exceptions.md when an exception turns out to be a real bug — for example, after a refactor changes the threat model or the Council pass (/council audit-review) marks a previously-suppressed finding disputed.

sergei-aronsen/claude-code-toolkit

Command

Append a structured exception entry to .claude/rules/audit-exceptions.md after the user has confirmed a finding is not exploitable. Future /audit runs consult this file in Phase 0 and skip matching findings.

sergei-aronsen/claude-code-toolkit

Command

Run a structured project audit (security / performance / code-review / deploy-checklist / DB-performance / design-review) with FP recheck, allowlist suppression, and a mandatory Council pass.

sergei-aronsen/claude-code-toolkit

Command

Empty the Supreme Council content-hash cache at /.claude/council/cache.

sergei-aronsen/claude-code-toolkit

Command

Show Supreme Council usage and cost summary from /.claude/council/usage.jsonl.

sergei-aronsen/claude-code-toolkit

Command

Challenge an implementation plan with Gemini (The Skeptic) and ChatGPT (The Pragmatist) before coding. The Council is not a linter — it validates whether the approach is justified, well-scoped, and free of common production-readiness traps.

sergei-aronsen/claude-code-toolkit

Command

Pick a brand-inspired DESIGN.md and drop it into the project so coding agents can generate a matching UI.

sergei-aronsen/claude-code-toolkit

Command

Walk a failing CI run through a 7-step diagnosis loop — fetch the failure, classify the layer, isolate the offending change, reproduce locally, fix, verify, and learn. Designed for the case where CI fails on a PR and you need to triage without bouncing between browser tabs and terminal.

sergei-aronsen/claude-code-toolkit

Command

Verify a single factual claim against current web sources. Returns a verdict (VERIFIED, DISPUTED, UNVERIFIABLE) with supporting citations.

sergei-aronsen/claude-code-toolkit

Command

Extract problem solutions and save them as scoped rule files that auto-load only for relevant files.

sergei-aronsen/claude-code-toolkit

Command

Quick web search with synthesized answer and citations through your Perplexity Pro subscription. Runs in search mode (Sonar) — single-pass, fewer sources, much faster than /research.

sergei-aronsen/claude-code-toolkit

Command

Pack the current repository (or a remote one) into a single AI-friendly file via Repomix. The output lands in .claude/scratchpad/ and is ready to attach to any LLM — ChatGPT, Claude web, Gemini, a teammate, an issue thread.

sergei-aronsen/claude-code-toolkit

Command

Multi-persona business review of a feature plan or SPEC. Parallel to /council but focused on product/marketing/economics, not technical correctness. Invokes product-thinking skill if .planning/product/ .md is missing, then runs persona review.

sergei-aronsen/claude-code-toolkit

Command

Audit a system prompt (CLAUDE.md, agent definition, slash command, custom GPT prompt, Cursor rules file, Telegram bot prompt, etc.) against the canonical 7-block system prompt architecture documented in components/system-prompt-architecture.md. Returns a per-block grade, lists missing structure, and proposes drop-in…

sergei-aronsen/claude-code-toolkit

Command

Rewrite a single prompt file into a deployment-ready version. Companion to /council — where the Council validates a plan with Skeptic + Pragmatist review, the Prompt Engineer rewrites one prompt for clarity, controllability, reliability, and reusability. Drives one of three provider CLIs: Claude Code (claude -p)…

sergei-aronsen/claude-code-toolkit

Command

Run deep, multi-source research with citations through your Perplexity Pro subscription instead of paying per-token for the Sonar API. Routes through the optional comet-bridge MCP that talks to a locally-running Comet browser where you are logged into Perplexity.

sergei-aronsen/claude-code-toolkit

Command

(Re)generate the local HTML post-install setup guide for installed components and MCPs, then open it in the browser.

sergei-aronsen/claude-code-toolkit

Command

Open the dependency update dashboard — shows installed vs latest versions for every tracked toolkit dependency (Layer 1/2/3) in an aligned table. User picks what to upgrade via a one-keystroke prompt (a/o/c/n) plus a comma-list custom mode. Manual control, no auto-update.

sergei-aronsen/claude-code-toolkit

Command

Smart update of Claude Code Toolkit — updates system files while preserving your customizations.

sergei-aronsen/claude-code-toolkit

Command

Quarterly external dependency risk review — checks GSD, Superpowers, Morph, better-model, claude-context for maintainer activity, breaking change cadence, license drift.

sergei-aronsen/claude-code-toolkit

Command

Functional diff analysis of pinned external vendors (Superpowers, GSD, Serena, better-model, claude-context, cc-safety-net, RTK). Clones fresh sources, diffs against manifest.json:vendorpins, classifies each change as BREAKING / ADOPT / IGNORE / DEPRECATE. Use this when the toolkit user wants to know what changed…