LLM Mart Basic

State-of-the-art secrets management for building and auditing software. Use whenever a task involves creating, storing, injecting, rotating, or scanning for credentials — or reviewing code/infrastructure for secret leaks and misuse. BUILD mode: implementing secrets handling; AUDI

State-of-the-art security & compliance engineering (2026) for the cybersecurity control frameworks and product-security regulations that drive architecture, code, and CI gates — not the organizational policy binder. Use when work must satisfy or be audited against NIST CSF 2.0, S

State-of-the-art shell scripting (bash-focused, defensive) for writing and auditing shell scripts, CI scripts, init/deploy scripts, container entrypoints, and Makefile recipes — and, just as much, for the ad-hoc commands you run yourself: a grep/find/rg sweep whose result you are

State-of-the-art software testing strategy and practice (2026) for designing test strategy, writing unit/integration/e2e tests, or auditing test suites. Covers suite shape (pyramid/trophy/honeycomb), test design quality (behavior-first, AAA, determinism, smells), test doubles (mo

State-of-the-art threat modeling for both designing new systems and auditing existing ones. Use when designing a feature, service, integration, or architecture that touches untrusted input, new trust boundaries, sensitive data, or third-party dependencies (BUILD mode), and when r

State-of-the-art UX writing and product-copy guidance (2026) covering voice and tone systems, plain language (ISO 24495-1), microcopy (buttons, labels, empty states, onboarding, notifications), error and feedback message craft, and the accessibility and localization of interface

State-of-the-art engineering rules (2026) for the JavaScript SSR meta-frameworks: React 19 + Next.js (App Router, React Server Components, Server Actions) and Vue 3 + Nuxt 4 (Nitro server routes, composables) — plus the cross-cutting concerns of server rendering: hydration correc

Give this repo's CLAUDE.md / AGENTS.md a checkup — size vitals vs official guidance, dead references, dead commands, stale claims — then backtest every rule against the repo's own Claude Code session history to see which rules were actually followed, ignored, or never used, and p

Example skill loaded from resources_discover

Creates implementation plans from context and requirements

Code review specialist for quality and security analysis

Fast codebase recon that returns compressed context for handoff to other agents

General-purpose subagent with full capabilities, isolated context

Git-backed control plane for AI-agent skills, tools, context, permissions, and identity. Self-hosted and MCP-native.

在 WorkBuddy 中下载并配置 dsh-plugin-garmin-connect npm 包，通过 MCP 工具分析 Garmin 活动、睡眠、步数、心率、体重、训练库、跑步趋势和有限的恢复信息，也可按用户要求创建 Garmin 训练或下载活动 FIT 文件。适用于 Garmin 配置、回顾、比较和明确授权的写操作；不用于医疗诊断。

GitHub Actions, required checks, TestMu, OS matrix, and merge gates for Skill Doctor. Use when editing workflows, adding CI jobs, deciding what runs on every commit, or wiring crates/npm publish.

Skill Doctor CLI UX, flags, exit codes, text/JSON/SARIF reports. Use when changing clap, printers, GitHub Action inputs, or CI gate flags.

SD-11 scanner-mediated injection — neutralize untrusted skill bytes before any model; additive-only scoring. Use when touching L2, MCP, prompts, envelopes, or scoring merge.

Skill Doctor product and architecture context. Use at the start of a session, when deciding where code lives, when the user asks how the scanner works, or before any non-trivial change.

Pre-publish and publish path for crates.io, npm installer, GitHub Releases, SBOM. Use when cutting versions, editing release.yml, or adding publish steps. Never publish from a feature branch.

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

Your efficient agentic AI coding CLI assistant

AI coding with Aegis governance built into execution: baseline-aware changes, evidence-backed delivery. Free desktop client, your choice of model. 将哲科思维融入 AI 开发…

Android in docker solution with noVNC supported, video recording, mcp server and AI-agent

Your AI assistant, built for the agentic era. Open source and local: talk to it, and it runs your agents, your coding CLIs, your browser and your apps. Windows,…

Verifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.

Let Claude Code and other coding agents drive and debug Chrome from the shell. DOM, network, console and raw CDP as short commands, no screenshots and no MCP ne…

Unofficial, agent-friendly Mercadona shopping CLI (Go) — search products, read prices, build a cart and prepare checkout from the terminal. BYO credentials.

Local-first AI canvas for visual workflows, AI short drama, image/video generation, storyboarding and asset management. ComfyUI, AI agents, MCP & Blender. 本地优先…

Let any AI coding tool — Claude Code, Cursor, Codex — drive your real Chrome. One-prompt setup, muscle memory, local-first.

runs anywhere. uses anything