LLM Mart Basic

Execute an implementation plan file produced by $draft-plan or $turboplan. Runs pre-implementation prep, then runs $implement to execute the steps and finalize once they are all done. Use when the user asks to "implement plan", "implement the plan", "execute the plan", "run the p

Interpret third-party feedback by running parallel internal and peer interpretations to surface intent, correctness concerns, and ambiguities. Use when the user asks to "interpret feedback", "interpret comments", "what does this feedback mean", "clarify reviewer intent", "underst

Systematically investigate bugs, test failures, build errors, performance issues, or unexpected behavior by cycling through characterize-isolate-hypothesize-test steps. Use when the user asks to "investigate this bug", "debug this", "figure out why this fails", "find the root cau

Deep architecture report that fans out parallel inspections across different aspects of the codebase (structure, tech stack, APIs, patterns, data flow, dependencies, testing) and synthesizes findings into a comprehensive document at .turbo/codebase-map.md and .turbo/codebase-map.

Capture an out-of-scope improvement opportunity so it doesn't get lost. Use when the user asks to "note improvement", "save improvement", "track this for later", "remember this improvement", "note this idea", "log improvement", "backlog this", or "park this idea". Also invoke pro

Developer onboarding guide that composes architecture mapping, tooling review, and agentic setup review with setup, troubleshooting, and next-steps agents to produce a comprehensive guide at .turbo/onboarding.md and .turbo/onboarding.html. Use when the user asks to "onboard me",

Run an independent peer review via Claude. Use when the user asks to "peer review", "peer review my code", "peer review my plan", "get a second opinion", or "independent review".

Fetch and rank open GitHub issues by community engagement, present the top 3 candidates, and plan implementation for the selected issue. Use when the user asks to "pick next issue", "next issue", "which issue should I work on", "top issues", "most popular issues", "prioritize iss

Stage, format, lint, test, review, smoke test, and re-run itself until stable. Use when the user asks to "polish code", "refine code", "iterate on code quality", "review loop", "clean up, test, and review loop", or "run the polish loop".

Stand up the project's live app and hand it to the user to try a change firsthand, then gate on their verdict before continuing. Use when the user asks to "preview the change", "let me try it", "spin up the app so I can test it", "set it up so I can poke at it", or before finaliz

Recall the reasoning behind a past change from Codex session history when available, falling back to commit diff and surrounding code. Use when the user asks to "recall reasoning", "find reasoning", "look up reasoning", "recall implementation reasoning", "find the rationale", "wh

Iteratively review and revise a plan until no new findings survive evaluation. Use when the user asks to "refine the plan", "iterate on the plan", "tighten the plan", or "improve the plan".

Draft, confirm, and post a single conversational reply to GitHub PR conversation comments (issue comments). The reply addresses all tracked items in one natural-prose message. Use when the user asks to "reply to PR conversation", "post PR conversation replies", or "draft PR conve

Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draf

Choose an implementation path (direct or plan) for evaluated findings and dispatch it. Direct path applies fixes directly; plan path runs $turboplan. Use after $evaluate-findings has tagged findings and they need to be implemented, or when the user asks to "resolve findings", "ap

Evaluate, fix, answer, and reply to GitHub pull request review comments and conversation comments. Handles both change requests (fix or skip) and reviewer questions (explain using reasoning recalled from past Codex session history). Use when the user asks to "resolve PR comments"

Detect agentic coding infrastructure in a project: CLAUDE.md, AGENTS.md, installed skills, MCP servers, hooks, and cross-tool compatibility (Claude Code and Codex CLI). Returns structured findings about agentic readiness without applying changes. Use when the user asks to "review

Review code for bugs, security vulnerabilities, API misuse, consistency issues, simplicity problems, or test coverage gaps by running internal reviews and a peer review in parallel and returning combined findings. Single-concern with a type argument, or full review with no argume

Detect package managers and discover outdated or vulnerable dependencies. Returns structured findings without upgrading. Use when the user asks to "review dependencies", "check for outdated packages", "check dependencies", "scan dependencies", or "dependency review".

Review a plan by running internal reviews and a peer review in parallel and returning combined findings. Use when the user asks to "review my plan", "check my plan", "critique my plan", or wants feedback on a plan.

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.

Use MCP Inspector to connect to local or remote servers, inspect capabilities, call tools, read resources, test prompts, and diagnose failures before release.

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

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat ap…

Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evid…

Ultimate Multi-Agent OS for Autonomous AI NPCs 2026

Personal AI Agent Hub 2026 — Build Your 24/7 Autonomous Assistant

Proven 2026 Multi-Agent AI Review System – Verdict-Driven Quality Control

Slash API Batch: Cut AI Costs by 50% in 2026

Web dashboard for Hermes Agent — multi-platform AI chat, session management, scheduled jobs, usage analytics

Agent Skills for Solopreneurs

AirLLM dramatically reduces inference memory usage, letting 70B large language models run on a single 4GB GPU card

Zero, your trustworthy AI teammate for real work.

一套 DSH runtime，Desktop、Web 与 TUI 三种开发体验。

Open-source operational advisor for ClickHouse — real-time monitoring plus AI-driven index/partition/materialized-view recommendations.

⚙️ TypeScript Style Guide and Agent Skill. A concise set of conventions and best practices for consistent, maintainable code.

Framework for AI agents to build and maintain a digital brain through Obsidian wiki

Apache Maka (Incubating) is a local-first AI agent workspace. Model messages, tool calls, tool results, permission decisions, and termination events are recorde…

Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active H…

Agentic development harness for Claude Code — SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control. Sin…

NocoBase is an open-source AI + no-code platform for building business systems fast. Instead of generating everything from scratch, AI works on top of productio…

An open-source AI coding agent that lives in your terminal.

PawWork — free, open-source desktop AI agent for macOS and Windows. Alternative to Codex App and Claude Cowork. BYOK with 75+ providers, ChatGPT OAuth, local mo…