LLM Mart Basic

Create a CHANGELOG.md following keepachangelog.com conventions with version history backfilled from GitHub releases or git tags. Use when the user asks to "create a changelog", "add a changelog", "initialize changelog", "start a changelog", "set up changelog", "generate changelog

Write a handoff file at .turbo/handoff/<YYYY-MM-DD>-<slug>.md capturing current session state — task, status, open decisions, in-flight changes, next step — so a fresh session can continue without re-deriving context. Use when the user asks to "create a handoff", "create handoff"

Create a GitHub issue with a drafted title and body. Use when the user asks to "create an issue", "file an issue", "open an issue", "submit an issue", "report a bug", "file a bug report", "file a feature request", or "file a design proposal".

Create a GitHub pull request with a drafted title and description. Use when the user asks to "create a PR", "create a pull request", "open a PR", or "submit a PR".

Scans an existing codebase and generates project-specific skills that capture inferred conventions such as naming, file organization, framework usage, data access, error handling, and testing style. Writes into the project's chosen skill directory (e.g., `.claude/skills/`, `.agen

Create a new skill or update an existing skill that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations. Use when the user asks to "create a skill", "make a new skill", "build a skill", "scaffold a skill", "write a skill for...", or "new skill

Analyze what changed and generate a structured test plan at .turbo/test-plans/<slug>.md covering four escalating levels: basic functionality, complex operations, adversarial testing, and cross-cutting scenarios. Use when the user asks to "create a test plan", "plan tests", "what

Analyze a codebase and produce a structured threat model at .turbo/threat-model.md covering assets, trust boundaries, attack surfaces with existing mitigations, attacker stories, and calibrated severity. Use when the user asks to "create a threat model", "threat model", "threat m

Align on the shape of a change through an interview, then implement it. Escalates open product decisions and settles the implementation shape in conversation. Use when the user asks to "discuss this change", "align on this change first", "ask me questions first", "interview me th

Produce an implementation plan at .turbo/plans/<slug>.md. Use when the user asks to "draft a plan", "draft the plan", "write an implementation plan", "plan this change", "create an implementation plan", or needs a first-draft plan file before refinement.

Critically assess external feedback (code reviews, AI reviewers, PR comments) and decide which suggestions to apply using adversarial verification. Use when the user asks to "evaluate findings", "assess review comments", "triage review feedback", "evaluate review output", or "fil

Explain whatever the user is pointing at right now in plain language: a pending question, a piece of code, an error, a command output, or an artifact like a plan or findings report. Use when the user asks to "explain this", "what am I being asked", "what's happening right now", "

Execute multi-level exploratory testing of the app covering basic functionality, complex operations, adversarial testing, and cross-cutting scenarios, plus usability observations through a UX lens reported separately from defects. Deeper than $smoke-test. Use when the user asks t

Fetch and summarize review feedback and conversation from a GitHub PR (unresolved review threads, review bodies, and PR conversation comments) without making changes. Use when the user asks to "fetch PR comments", "show PR comments", "check PR for unresolved comments", "list revi

Run the post-implementation quality assurance workflow including tests, code polishing, review, and commit. Use when the user asks to "finalize implementation", "finalize changes", "wrap up implementation", "finish up", "ready to commit", or "run QA workflow".

Find dead code using parallel sub-agent analysis and optional CLI tools, treating code only referenced from tests as dead. Use when the user asks to "find dead code", "find unused code", "find unused exports", "find unreferenced functions", "clean up dead code", or "what code is

Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build landing pages, websites, dashboards, web components, or any frontend UI. Generates creative, polished code that avoids generic AI aesthetics.

Shared writing style rules for GitHub-facing output (PR comments, PR descriptions, PR titles, issues, design proposals). Differentiates insider vs outsider voice based on author association. Not typically invoked directly — loaded by other skills before composing GitHub text.

Load code-style and task-specific skills, make the change described by the current context, then run post-implementation QA. Use for ad-hoc changes when no plan file or improvements backlog governs the work, and when the user asks to "just implement", "implement directly", "imple

Validate improvements from .turbo/improvements.md, recommend a working set tailored to what's in the backlog, and run one lane: direct fixes, investigation, or planned work. One lane per session. Use when the user asks to "implement improvements", "work on improvements", "address

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…