LLM Mart Basic

Use when auditing the developer-facing surface of a CLI, SDK, library, or package: API contracts, errors, public types, onboarding, and config.

Use when recent resolved feedback may reveal a broader recurring defect pattern across the project surface. Not for source-level feedback collection: use feedback-sweep.

Use when one named review viewpoint must run fix cycles until a fresh reviewer finds nothing. Not for multi-viewpoint review or remote, credential, publish, deploy, or irreversible changes.

Use when the user invokes this skill to generate targeted questions proving the author understands the change's codebase effect. Not for reviewing the change: use review.

Use when asked to review a pull request, examine code changes, find bugs, or audit a branch, in standard or depth mode. Not for an iterative review-and-fix loop: use audit-project.

Use when the user wants a per-finding visual walk through a diff or PR. Not for written review reports: use review. Not for codebase tours: use show-me.

Use when implementation must be checked against an authoritative specification, or during PR review for spec drift against checked-in specs. Not for spec updates: use spec-driven-implementation.

Use when the user runs /browser-qa for report-only QA results without entering a fix loop. Not for remote, credential, publish, deploy, or irreversible changes.

Use when asked to reproduce, profile, or verify CLI/TUI behavior. Produces a deterministic transcript or profile proof with session cleanup. Not for CLI design advice, use cli-for-agents.

Use when asked to verify or reproduce browser or Electron UI behavior with before-and-after evidence and no leftover processes. Not for remote, credential, publish, deploy, or irreversible changes.

Use when asked to prove coverage, find missing cases, or enumerate state, decision, requirement, or behavior space. Not for round-based or single-property tests: use askme, property-test-authoring.

Use when a complete product needs production-like acceptance evidence against documented acceptance criteria. Not for single-component evaluation or evaluation without documented criteria.

Use when verification is looping, would re-run untouched code, or duplicates an established proof. Not for tasks that require source or remote-system changes.

Use when a test surface needs behavior-guarding coverage raised to a configured target with mutation kill evidence. Not for line-coverage inflation without mutation proof.

Use when asked to initialize, scope, estimate, configure, validate, or optimize a mewt, muton, or mutation testing campaign before execution. Writes the TOML config. Not for running it: use the mewt CLI.

Use when a mutation campaign leaves surviving mutants needing triage. Classifies each as false-positive, missing-test, genotoxic, or removable. Not for setup: use mutation-campaign-configuration.

Use when a product surface must be tested against extreme or hostile worlds. Not for design disputes: use possible-worlds. Not for remote, credential, publish, deploy, or irreversible changes.

Use when property-based testing, theorem proving, or formal proof tactics require zero unproven properties. Not for remote, credential, publish, deploy, or irreversible changes.

Operate explicit orchestrator, implementer, validator, and scribe roles through a caller-selected agent runtime. Triggers: "agent-native factory", "role-shaped agent panes", "persistent workers".

Use an explicitly selected AGY runtime for one provided packet or fresh validator context. Triggers: "agy", "antigravity", "AGY evidence".

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

Open-source dots for the web: an AI agent with its own browser, one that does not get blocked.

Free MIT AI coding agent — no API key needed. Built-in free model, or bring Claude, GPT, Gemini, DeepSeek, Ollama +50 more. Swarm mode, 40+ tools, browser & des…

Open-source AI customer support system. AI-first support, human-ready operations.

A durable, multiplayer, mobile-first web app for Pi agents, built on Pi Durable

Embedded Cypher knowledge graph for Python and Rust. Bundled MCP server, describe() schema, and code-graph parser for LLM agents.

Turn PDFs, books and papers into interactive learning webpages｜将复杂材料转化为可追溯、可测验、可做笔记的学习网页

PhysicsOS 是一个面向初高中物理学习的公益可视化智能体，通过 AI 理解题目并结合物理引擎，将抽象物理过程转化为可交互、可观察、可计算、可验证的真实物理场景。