LLM Mart Basic

Flip the session into coordinator mode — the parent agent plans, scopes, reviews, and ships, but delegates all real work (exploration, implementation, review, fixes) to sub-agents routed by an empirically benchmarked model capability table. Use when the user invokes /orchestrate

Drive one tracked ticket from arrival to resolution through four verbs: triage, start, revise, finalize. Use when the user says triage/start/revise/finalize with a ticket id, asks to turn a ticket into a locked brief, to execute a work order, to action a review round on a ticket'

Lifecycle for user-facing surfaces — revise a shipped surface in the running app, lock a greenfield visual spec, build to a lock, critique/audit/polish a UI, or re-settle a locked term. Use for any request to design, review, or verify rendered UI (screens, dashboards, flows, comp

Register maintained or ephemeral Git checkouts with codebase-memory-mcp, keep long-lived indexes current through non-clobbering Git hooks, and tear down ephemeral indexes by exact deterministic identity. Use when asked to index, onboard, register, remove, or keep a repository cur

Vocabulary and principles for well-designed CI. Use when the user wants to design, review, or audit CI, says CI is noisy, slow, or expensive, or is designing a workflow yml.

Review the changes since a fixed point (commit, branch, tag, PR, or merge-base) on two axes — Standards (does it follow this repo's documented rules?) and Spec (does it do what the originating issue asked?). Each axis returns a verdict per enumerated item rather than an open-ende

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

Use the codebase knowledge graph for structural code queries, trace call paths and dependencies, inspect architecture, assess change impact, or activate the bundled Claude Code discovery hooks.

Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.

Launch or connect to a local development web server and drive it with a reusable headless-Chromium command interface. Use when asked to render, smoke-test, interact with, verify, or screenshot a local frontend or HTML mockup.

Produce a decision-safe handoff for a fresh agent. Use when a task changes hands, a session is ending midstream, a user asks for a handoff, or an agent needs to preserve a design/map/implementation decision without making the next agent rediscover it.

Convene a small panel of persistent reviewer personas (curated colleague-likenesses plus invent-on-demand) to review a document cold, in character, then synthesize a panel verdict. Use when the user wants a document reviewed by a panel, wants named perspectives on a plan or desig

Adversarially review a plan, work order, spec, or agent brief before anything gets built. Use when the user wants a plan reviewed, stress-tested, audited, or countersigned, says "plan review" or "poke holes in this plan", or wants a pre-build check on an issue/brief/PRD.

Write a pull-request body and score it before the PR is opened, or audit an existing PR's body against the same rubric. Use when about to run gh pr create, when a PR body needs writing or rewriting, or when asked whether a PR description is any good. Invoked as /pr-body write <bo

Use when a plan, spec, work order, or process doc is drafted and about to enter review or execution — grounds its facts, spikes its first hour, and single-sources its rules so review rounds start deep instead of shallow.

Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route.

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

Shape every response for a reader who wants the answer first and nothing after it. Answer-first structure, numbered steps, domain language governed by a per-repo glossary of approved terms, one instruction per sentence, no preamble or recap. Invoke with /say-less for full shaping

Create an isolated Git worktree for issue, pull-request, branch, or parallel agent work without editing the control checkout. Use when starting task work from fresh remote state, avoiding a dirty or shared checkout, or preparing a dedicated worktree for another agent.

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

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

Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, and operations, under your control.

An open-source Digital Worker platform for reliable execution, continuous co-evolution, and building Enterprise AI assets.

A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai

A governance harness for AI coding.

DeepSeek Harness 手机版：可直接安装的 Android APK，AI 免 Root 操作手机（Shizuku/root 可选），文件编辑只需所有文件访问权限，前台保活 + AI 通知

Local-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in.

Orbi — the factory that builds and operates AI software factories. GitHub Issues in, releases and runnable system out

Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.

The SDK for browser agents. Interact, search, extract, and fetch any site reliably across the web

Agent-native shopping for extreme value: verifiable same-product price evidence, checkout, orders, delivery, and after-sales.

The extensible power-user platform for Google Antigravity. Adds a native In-App Browser, animated Desktop Pets, revamped Gemini UI, and custom BYOK Gemini Pro k…

Open-source, single-binary, self-hosted AI agent — your models and data stay on your machine. A coding agent on par with Claude Code and a personal assistant li…

Your pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH · Claude Code · Code…

Bridge between QQ (SnowLuma OneBot v11) and DeepSeek Harness agents: social simulation, safe MCP tools, slang learning and more.

A 7×6 framework for agent architecture. 28 patterns, each placed at a coordinate, runnable Python code with verified engineering slices from Claude Code, Aider,…

针对 AI 自动化渗透 Agent 的新一代反制蜜罐，通过反向代理将API密饵载入真实业务、反向提示词注入等方式反制自动化渗透 Agent，实现多款主流通用Agent的反制上线控制。

Open-source, local-first AI agent for coding and real work. BYOK models, MCP, skills, plugins, workflows, and private knowledge bases.

A free AI-agent toolbox for Android, 一站式安卓AI Agent工具箱

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. I…

Independent, unofficial CLI to edit CapCut and JianYing (剪映) projects — subtitles, timing, speed, volume, templates, cut long-form to shorts. No API needed, rea…