LLM Mart Basic

Reviews service-worker route-matching and caching-strategy choices (precache vs. cache-first vs. network-first vs. stale-while-revalidate) against request type and security sensitivity, rejecting uniform blanket strategies and flagging authenticated/PII responses cached in the Ca

Diagnoses hydration-mismatch errors and streaming/Suspense-boundary structural issues to their specific root cause — non-deterministic rendering source, missing error boundary, serial data-fetch waterfall, or premature auth-unchecked streaming — grounded in the exact React/Next.j

Reviews whether data is correctly classified as server state, client state, or derived state, and whether the resulting store/cache design (query keys, invalidation, optimistic-update rollback, SSR instantiation, selector shape) avoids duplication, stale-data bugs, and unnecessar

Statically review SvelteKit form actions, load functions, hooks, and templates for CSRF origin-check bypass (checkOrigin/trustedOrigins), unauthenticated sensitive-data returns from load(), auth guards confined to +layout.server.js without an enforced parent()/hooks check, insecu

Statically review SvelteKit forms and form actions for functional resilience without JavaScript (native method="POST" fallback) and for use:enhance customization correctness (ActionResult branch handling, cancel() feedback, redirect/invalidation behavior), flagging silent-failure

Statically review SvelteKit route files (+page.js, +page.server.js, +layout.js, +layout.server.js, +server.ts) to verify universal-vs-server load placement, catching server-only secrets, database clients, or privileged API access that would leak into or execute inside the browser

Verifies that a bundler's tree-shaking actually eliminated dead code by inspecting output bytes and sideEffects/module-format configuration, rather than trusting a clean build as proof of elimination.

Review TypeScript diffs and tsconfig strictness posture for sound type contracts — auditing any/assertion usage at trust boundaries, unsound narrowing, and exported public-API type-surface breakage — so that a passing compile is meaningful evidence rather than a decorative pass,

Reviews Storybook visual-testing setup -- test-runner wiring, Chromatic integration, and the a11y addon's axe-core gating -- to ensure visually-critical components have deterministic pixel-diff and accessibility coverage before merge, grounded in current Storybook docs.

Statically review Vue 3 Composition API code — composable extraction quality, reactivity-boundary correctness (ref/reactive/computed usage, destructuring-loses-reactivity pitfalls), and script-setup component organization — against Vue's own documented composable conventions and

Statically review Vue Router navigation guards, redirect flows, and template bindings for client-side guards used as the sole authorization boundary, open redirects via route.query.redirect/returnUrl, javascript:/data: scheme injection through dynamic :to/:href bindings, route pa

Statically review Vue 3 SSR entry points and templates for cross-request state pollution (module-scope reactive state, non-per-request app/store creation) and injection via unsanitized v-html or unvalidated dynamic href/src bindings, grounded in Vue's own SSR and security-best-pr

Statically review Pinia and legacy Vuex state stores for sensitive data persisted to localStorage/sessionStorage without scoping, untrusted server-payload hydration (window.__pinia/__INITIAL_STATE__) with un-escaped state serialization, SSR store-singleton cross-request pollution

Audit frontend markup, components, and design-system primitives against WCAG 2.2 Level A/AA success criteria and ARIA APG interaction patterns, separating automated-detectable violations from manual-verification-required items and flagging legal exposure, with reference material

Design and build AI-powered applications on AlloyDB for PostgreSQL using AlloyDB AI — covering vector search, hybrid search (vector + full-text), AI SQL functions (ai_generate, ai_classify, ai_score, ai_embed), model endpoint management, and the AlloyDB Omni edge runtime. Prefer

Operate AlloyDB clusters and Cloud SQL instances — HA configuration, read replicas, connection pooling, maintenance windows, backup strategy, and performance diagnostics.

Design and operate Anthos / GKE Enterprise fleet management, Config Management (GitOps with Policy Controller), multi-cloud Kubernetes across GCP, AWS, and Azure.

Design and operate Apigee X API proxies — rate limiting, OAuth/JWT security policies, quota plans, developer portal setup, and API product management.

Analyze BigQuery slot reservation sizing, BI Engine acceleration, query cost estimation, dataset governance (expiration, access controls), and partitioning/clustering optimization to reduce on-demand scan costs.

Review GCP Certificate Manager and classic Google-managed TLS certificates — certificate map configuration, DNS authorization, CAA record validation, certificate rotation automation, wildcard vs SAN design, and expiry monitoring.

Fourteen posts of being wrong in production, compressed to checkboxes

Healthy nodes, a quiet network, 300 restarts in three days, and a latency budget measured in milliseconds

Discovery worked. Ping worked. Every TCP connection timed out, and later the tunnel only worked when someone had a terminal open.

Every VM came back. The cluster did not. Declarative systems converge on config, and the datapath isn't config.

A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.

A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.

None of the safety came from the model. It came from six boring habits.

Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.

Six hours in, one step left, everything green, and the incident that didn't happen

CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.

Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it

An API request routing a model's tool call through an approval gate to a remote MCP server

31 config keys, two audits, and why the first one was wrong in both directions

The official MCP Registry stores standardized server metadata rather than package code. Publishers verify a namespace, describe installation or remote access, and submit immutable versions.

Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.

Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.

"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks

stdio fits local processes and prototypes. Streamable HTTP fits hosted services and shared integrations. The right choice follows where the capability runs and who must reach it.

The most important rule wasn't about what I could change. It was about what I was allowed to display.

Tools perform operations, resources expose readable context, and prompts provide reusable templates. Choosing the correct primitive makes an MCP server easier to understand and govern.

Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable checkpoints. Usage: /autopilot target.com [--paranoid|--normal|--yolo]

Build an exploit chain — given bug A, finds B and C to combine for higher severity and payout. Knows common chain patterns: IDOR→ATO, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth. Usage: /chain

Active vulnerability hunting. Two-track dispatcher — asks Red Team vs WAPT, hands off to hunt-dispatch skill and sibling commands. Usage: /hunt target.com | /hunt *.target.com | /hunt targets.txt [--vuln-class X] [--source-code P] [--chrome]

On-demand intelligence fetch for a target — CVEs, disclosed reports, new features. Pulls NVD/GitHub-Advisory CVEs + bundled disclosed reports + hunt memory context. Usage: /intel target.com

Inspect or rotate the autopilot ledger JSONL files (findings.jsonl, negatives.jsonl). Caps file size and keeps N rotated backups so memory does not grow unbounded.

Pick up a previous hunt on a target — shows hunt history and untested surface from the autopilot ledger. Usage: /pickup target.com

Run full recon pipeline on a target — subdomain enum (Chaos API + subfinder), live host discovery (dnsx + httpx), URL crawl (katana + waybackurls + gau), gf pattern classification, nuclei scan. Outputs to recon/<target>/ directory. Usage: /recon target.com

Optional manual note on a target or the last confirmed finding. Capture is automatic during autopilot; this is for extra context. Usage: /remember

Write a submission-ready bug bounty report. Generates H1/Bugcrowd/Intigriti/Immunefi format with CVSS 3.1 score, proof of concept, impact statement, and remediation. Run /validate first. Usage: /report

Mandatory pre-flight scope check — verify an asset is in scope BEFORE any HTTP touch. Deterministic (deny-wins, default-deny) via engine/scope.py against the engagement's scope.md. Blocks out-of-scope testing. Usage: /scope <asset> [<asset> ...]

Show ranked attack surface for a target from its recon manifest + hunt memory. Deterministic backing is `cbh surface <target>` (reads recon/<target>/manifest.json); LLM layer adds ledger signal. Usage: /surface target.com

Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP lock bypass, authority retention, bonding curve exploits, fake renounce, sandwich amplification). Manual 8-class grep audit (with an optional automated scanner if present). Usage: /token-scan <contract_path_or_dir> [--chain solana]

Quick 7-Question Gate triage on a finding before writing a report. Kills N/A submissions before they happen. Faster than /validate — for quick go/no-go decisions. Usage: /triage

Validate a finding — runs 7-Question Gate + 4-gate checklist. Kills weak findings before report writing. Prevents N/A submissions that hurt validity ratio. Usage: /validate

Smart contract security audit — runs through 10 bug class checklist (accounting desync, access control, incomplete path, off-by-one, oracle errors, ERC4626, reentrancy, flash loan, signature replay, proxy/upgrade). Applies pre-dive kill signals first. Generates Foundry PoC template for confirmed findings. Usage: /web3-audit <contract.sol>

Crabbox is a single CLI (`crabbox`). Commands are top-level, not nested under a

`crabbox actions` prepares a leased box from your repository's own GitHub

See [Runtime adapter stack](../features/runtime-adapter-stack.md) for the

`crabbox admin` groups trusted operator controls for coordinator-backed leases and the cloud resources behind them. Use it to inspect every lease the broker tracks, reconcile expired leases against live cloud state, force-release or delete a backing server, print provider IAM pol

`crabbox artifacts` turns a desktop lease into durable QA evidence: it collects

Build AI Agents like playing LEGOs. Everything is a Plugin.

The coding agent that answers to you, your model, your machine, your rules.

CI-native agent CLI tool for deterministic pipeline gating.

Local-first cross-platform desktop workspace for Claude Code / agents: multi-agent, Git worktrees, code diffs, skill marketplace, multi-model, Computer Use, tas…

Local-first visual generation runtime and studio for people and coding agents, with reproducible image and video workflows across multiple providers.

A token-efficient MCP server for safe, line-oriented text file editing with partial reads, hash-based conflict detection, and atomic multi-file operations.

Open-source, evidence-driven MCP server for RTL simulation debugging: correlate VCS/Xcelium logs, VCD/FSDB waveforms, SystemVerilog/UVM source, hierarchy, and c…

runs anywhere. uses anything

One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher, per-run git worktrees, one review board.

Soul-driven AI agent with permission-hardened tools, token budgets, and multi-channel access. Runs 24/7 from CLI or Telegram.

Email, SMS & phone-call infrastructure for AI agents — send and receive real email and text messages, and place agent-driven outbound voice calls, all programma…

55 MCP tools to drive the Unity Editor from any MCP-compatible AI agent — scenes, GameObjects, prefabs, assets, tests, and builds. OpenClaw gateway included for…

Google Ads MCP + Meta Ads MCP + GA4 in one server for Claude, ChatGPT, Cursor & n8n — 250+ tools, hosted remote MCP, OAuth login, no API keys. By Ryze AI.

Claude Code & Codex 本地 token 追踪 — 状态栏（Codex 业界首创伪 statusline）、GitHub 风格热力图、多模型成本分析。 | Local token tracker for Claude Code & Codex — status line (industry-first…

Empower the Shell to think. Evolve Operations.

🤖 A full-stack Agent Chat Runtime for pre-production validation, built with act, TypeScript, and LangGraph JS combining streaming, multimodal, HITL, and tools…

Cerul — video memory infrastructure for AI products. SDKs, CLI, MCP, and developer integrations.

Stealth headless browser for AI agents — bypass Cloudflare, bot detection, and anti-scraping. Drop-in Puppeteer/Playwright replacement.

Web research for your agents with smart and safe tooling + knowledge store

FuXi is a fast, self-contained AI coding agent that lives in your terminal — edit code, run commands, and drive tools, with cost-aware routing across LLM provid…