LLM Mart Basic

Analyze task complexity and route to a mode by artifact: direct fix for clear-scope changes, or a plan file when the approach needs to be written down. Use when the user asks to "turboplan", "run turboplan", "plan this task", "turbo plan mode", "plan and implement", or "use turbo

Teach the user to deeply understand a change through interactive tutoring: restating understanding, drilling into why/what/how, and quizzing until mastery. The active counterpart to a one-shot explanation. Use when the user asks to "understand this change", "teach me this change"

Update the Unreleased section of CHANGELOG.md based on current changes. No-op if CHANGELOG.md does not exist. Use when the user asks to "update changelog", "add to changelog", "update the changelog", "changelog entry", "add changelog entry", or "log this change".

Upgrade project dependencies with breaking change research for major version updates. Use when the user asks to "update dependencies", "upgrade packages", "upgrade dependencies", "update deps", "upgrade deps", "update npm deps", "update Swift packages", "cargo update", "go get up

Update an existing GitHub pull request's title and description to reflect the current state of the branch. Use when the user asks to "update the PR", "update PR description", "update PR title", "refresh PR description", or "sync PR with changes".

Update installed Turbo skills from the local repo with a dynamic changelog, conflict resolution for customized skills, and guided user experience. Use when the user asks to "update turbo", "update turbo skills", "reinstall turbo", or "upgrade turbo".

Apply a UX lens to a user-facing change: whether it serves the user's real goal and whether the path through it holds together, using the Understanding, Bridging, and Flowing contexts. Use when scoping, planning, or assessing any change that affects what a user sees or does. Load

For each reviewer question on a PR, recall implementation reasoning and compose a raw answer. Use when the user asks to "answer reviewer questions", "draft answers to PR questions", or "explain reviewer questions".

Apply findings by making the suggested code changes. Applies accepted verdicts, escalates ambiguous findings to the user, and offers to note genuine improvements for later. Use when the user asks to "apply findings", "apply fixes", "apply suggestions", "apply accepted findings",

Assess project-wide structural technical debt: complexity hotspots, deprecated API usage, duplication clusters, and architecture rot. Ranks findings by impact and refactor effort into a report at .turbo/technical-debt.md. Use when the user asks to "assess technical debt", "find t

Project-wide health audit pipeline that fans out to all analysis skills in parallel, evaluates findings, and produces a unified report at .turbo/audit.md. Use when the user asks to "audit the project", "run a full audit", "project health check", "audit my code", "codebase audit",

Shared changelog conventions and formatting rules referenced by $create-changelog and $update-changelog. Not typically invoked directly.

Run a non-interactive Claude Code print-mode call from Codex. Use when the user asks to "claude print", "ask claude", "run claude", "consult claude", or when a Codex Turbo skill needs Claude as an independent peer reviewer.

Enforce existence, reuse, mirror, and symmetry principles to keep new code minimal and consistent with surrounding code. Use when writing new code in an existing codebase, adding new features, refactoring, or making any code changes.

Shared commit message rules and technical constraints referenced by $stage-commit and $commit-staged. Not typically invoked directly.

Commit already-staged changes with a message matching existing commit style. Use when the user asks to "commit staged changes" or "commit what's staged".

Commit already-staged changes and push in one step. Use when the user asks to "commit and push staged changes", "commit and push what's staged", or "commit staged and push".

Consult Claude Code for second opinions, brainstorming, or difficult debugging from Codex. Use when the user asks to "consult claude", "ask claude", "get claude's opinion", "brainstorm with claude", or "discuss with claude".

Consult ChatGPT Pro via ChatGPT browser automation for problems that resist standard approaches. Use when stuck on a very hard problem, when standard approaches have failed, when multiple debugging attempts haven't worked, or when the user says "ask the oracle", "consult oracle",

Propose a turbo skill improvement upstream by filing a GitHub issue against the turbo repo. Use when the user asks to "contribute to turbo", "submit turbo changes", "contribute back", "suggest a turbo improvement", or "upstream my changes".

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

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it.…

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

:memo: Vimlike Modal Text Editor in Rust

CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Hermes Agent memory plugin/provider for scope-aware recall, SQLite truth, LanceDB semantic search, and hybrid retrieval.

For You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式，带到每一个 AI 工具里。

A coding agent: give it a prompt and it reads, writes, runs commands, and searches code in a loop until the work is done, using native tool-calling across OpenA…

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and…

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

DeepSeek Harness Desktop (dsh-desktop). EAC: Embracing All Creation (揽尽万象). Bundled Node.js runtime with full dsh-CLI kernel, one-click startup, 10 built-in UI…

See your agent think. Zero-config observability & governance for 26 AI agent runtimes: Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Cline, Ope…

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP…

Yet another coding agent harness, lightweight and written in go.

a coding Agent from pi. ∞ providers, sub-agents, hashline edits, and a permission gate

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting…

🧠 Leon is your open-source personal assistant.

The Station, an open-world multi-agent environment that models a miniature scientific ecosystem.

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

VelaTerm = iTerm2 + Codex, The Best Terminal for AI Coding