LLM Mart Basic

The end-to-end procedure for one trade on the HyperGrok desk - from an idea to a reviewed, journaled result - with the ticket format, who owns each stage, and what "done" looks like. Use whenever the user wants to open, adjust or close a position, or whenever any Bot is about to

Read a Hyperliquid account from the desk computer - positions and margin, spot balances, open orders including trigger details, fills, funding paid, ledger updates, order status by oid or cloid, historical orders, portfolio history, fee tier and rate-limit budget - with curl and

Less common Hyperliquid actions and their rules - dead-man's switch (scheduleCancel), TWAP orders, spot orders, expiresAfter and nonces, API wallet approval from code, sub-account and vault addressing, HIP-3 dexs, and what the desk deliberately does not do (transfers, withdrawals

Compact reference for the Hyperliquid API as the desk uses it - endpoints and envelopes, every /info request type, every /exchange action with its signing scheme, order and status vocabularies, asset ids, tick and lot rules, rate limits, WebSocket subscription list, error strings

Read live Hyperliquid market data from the desk computer with curl or the Python SDK - mid, mark and oracle prices, order book depth, funding (current, predicted, historical), open interest, volume, candles, perp and spot metadata, margin tiers, and how to save datasets for the s

Place, cancel and modify Hyperliquid orders correctly from the desk computer - limit and IOC (market-style) orders, take-profit and stop-loss trigger orders with grouping, client order ids, reduce-only, batch actions, price and size rounding, and how to read every response status

Prepare the desk computer to work with Hyperliquid - install the SDKs, pick testnet or mainnet, verify connectivity, and (only when the user asks) provision a trade-only API wallet through the secure secret store and verify it is approved. Use during desk setup, when moving betwe

Subscribe to live Hyperliquid data over WebSocket from the desk computer - mids, order book, trades, candles, best bid/offer, and per-account fills, order updates and events - with raw JSON, Python SDK and TypeScript examples, plus how to run a supervised watch that logs to a fil

用证据链和 X/Y/Z 立体分析法研究产品、公司、技术、概念、人物、行业、市场或复杂事件，交付可追溯的深度研究报告。用户要求 deep research、系统调研、竞品或市场研究、尽职调查、来龙去脉分析、证据链或正式研究报告时使用。简单名词解释、新闻摘要、短篇观点、仿写，以及 3D 建模、渲染、CAD 或图形设计不使用。

起草或润色可直接发送的职场即时消息和邮件。用户明确要求“怎么说、怎么发、润色、改写、写消息、写邮件”，或提供职场素材并表明要发给某人时使用；仅展示背景、讨论沟通策略、撰写 PRD、报告或长篇文档时不使用。

Curated Agent Skills collection for AI-assisted development. Open standard — agentskills.io. Portable across Claude Code, Cursor, Copilot, Codex, Gemini CLI, an…

发布后独立质量循环——单盲四角色流水线（A 审 12 视角 → B 修 → C 验 → D 复核），每轮新 session 保证零上下文，连续 2 轮无 P0/P1 即停。

发版前自动验证闸门——V 验证 + F 修复循环（verdict FAIL → F 改代码 → 跑 audit → V 重验），最大 3 轮直到 PASS。纯只读验证 + 最小修复。

一次挂载 sofagent 全套能力——6 项能力一次到位（注入 · 审计与验收 · 经验 · 回溯 · 巡检 · FDE 三域）（seam: non-seam:plugin-suite）——只编排不重实现——sofagent 约束层在 DSH（DeepSeek Harness）生态的插件形态。

变更机器审阅 + 验收硬门禁——24 规则 + git diff 硬证据 + Turn 停止验收判定（验收不过不放行，开关独立可关）（seam: tools/result + tools/pre-execute + fs/write-intent + agent/turn-stopping）——桥接 @sofagent/audit runRules——DSH（DeepSeek Harness）cordis plugin。sofagent 约束层在 DeepSeek Harness 生态的插件形态。

7×24 巡检 + 健康监测 + webhook 推送（seam: non-seam:host-process）——桥接 @sofagent/daemon startCron——DSH（DeepSeek Harness）cordis plugin。sofagent 约束层在 DeepSeek Harness 生态的插件形态。

经验沉淀——think.md 反思 + Dream Cycle + evolve + instinct→skill + refine（seam: turn/end）——桥接 @sofagent/think generateThinkEntry——DSH（DeepSeek Harness）cordis plugin。sofagent 约束层在 DeepSeek Harness 生态的插件形态。

FDE 进场与能力流通——把企业业务梳理成 AI 能力，并让这些能力在企业内被发布、发现、调用、评价、退役（seam: non-seam:tool-set）——桥接 @sofagent/orchestrator publishCapability / @sofagent/ontology generateOntologyView / @sofagent/core restoreSnapshot——DSH（DeepSeek Harness）cordis plugin。sofagent 约束层在 DeepSeek Harness 生态的插件形态。

启动注入企业约束——四层加载链（seam: agent/pre-step）——桥接 @sofagent/harness buildConstrainedSystemPrompt——DSH（DeepSeek Harness）cordis plugin。sofagent 约束层在 DeepSeek Harness 生态的插件形态。

出错逆序撤销——git snapshot → effect disposer（seam: agent/error）——桥接 @sofagent/core getHistoryFilePath——DSH（DeepSeek Harness）cordis plugin。sofagent 约束层在 DeepSeek Harness 生态的插件形态。

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

PiG (Pi in Go) is a faithful Go port of upstream Pi, the TypeScript codebase behind the Pi coding agent. It is a parity-bound translation, not a rewrite: upstre…

An AI Agent that lives in your pocket. Local-first and privacy focused.

Unofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.

Adaptive Test-time Learning and Autonomous Specialization

Prediction-market trading engine — Wang Transform pricing on 291K+ contracts; paper-traded across Kalshi · Polymarket · Solana DFlow (Jito bundles) · 633 tests

Knowledge Management for Humans and Agents

Open-source Claude Cowork / Codex / WorkBuddy alternative — a local-first AI office agent that turns one request into real PPTX, DOCX, XLSX and HTML files. Runs…

DeepAgent Code: AI coding agent with persistent memory and control plane

Awesome Jev — evidence-graded index of TypeSafe System One: SDKs, MCP tools, agents, apps and open models. 20 languages, rebuilt every 2 hours.

CLI for Telegram — agent-friendly, daemon-based, with webhook event push.

AI deep-research agent that turns any question into a cited report: plans searches, reads real sources, verifies evidence. Self-hosted, multi-provider, Docker-r…

Event-stream AI Agent framework for building your persona bot 🍊

Give the agent a machine. Just not yours. Each AI coding agent gets its own isolated machine with root, Docker, and systemd - active defense detects and stops t…

Local Emperor-style AI agent with Vue WebUI, multi-provider LLMs, streaming chat, tools, skills, memory, and token telemetry.

Open-source AI reverse-engineering agent platform and MCP server for Ghidra, Frida, x64dbg and Rizin — automated PE/APK/binary analysis, CTF and malware researc…

"Never send a human to do a machine's job" - Open Source AI hacking agent

Prismer Cloud

My Personal Blog (Robotics)

Tau Coding Agent - like Pi, but twice as much

Open-source alternative to OpenAI Dots: self-hosted AI chat, tools, approvals, connectors, and computer tasks.