LLM Mart Basic

Maps a customer journey across stages, touchpoints, emotional curve, pain points, and moments of truth into a markdown artifact with an optional mermaid timeline or flowchart. Use when synthesizing existing research into the shape of a customer's experience, end-to-end or for one

Estimate market opportunity (TAM, SAM, SOM) using multiple sizing frameworks (top-down, bottom-up, comparable company, analogous market). Triangulates across frameworks, highlights where they converge and diverge as signal, and produces a calibrated range with source-graded confi

Runs a fast pre-build risk review on a product idea, feature request, or scope change, naming the single assumption most likely to make it fail and returning a clear verdict (build small, validate first, pivot first, or don't build yet) with a no-code validation step. Use before

Produces a topic-segmented post-meeting summary for attendees with decisions highlighted and actions captured inline per topic (plus a consolidated action view at the end). Auto-populates topic skeleton from a sibling meeting-agenda when available and reconciles planned vs. actua

Specifies what questions a dashboard must answer and the metrics, visualizations, filters, and data sources it needs, so data teams build something that informs decisions rather than displaying numbers. Use when requesting a dashboard or formalizing ad-hoc reporting. For the even

Analyze survey results into actionable PM insights. Produces persona segmentation, hypothesis validation status, thematic clustering of open-text responses, statistical confidence labels, prioritized recommendations, and what-NOT-to-conclude warnings. Refuses to overstate statist

Pre-sprint brief that locks challenge, sprint questions, team and role assignments, customer recruiting plan, prototype medium, interview format, logistics, and success criteria before Monday of a Design Sprint. Use after the readiness verdict is Go and before Monday begins. Prod

Day 3 (Wednesday) move of a Design Sprint that runs the art museum layout, heat map, speed critique, straw poll, Decider supervote, rumble-vs-all-in-one decision, and the storyboard that drives Thursday's prototype build. The most decision-heavy day of the sprint. Use Wednesday m

Day 1 (Monday) move of a Design Sprint that produces the bundled Monday artifact containing long-term goal, sprint questions (3-7 testable risks), customer or system map (5-15 step flow), expert interview notes, HMW (How Might We) cluster board, and the Decider's chosen target mo

Day 4 (Thursday) move of a Design Sprint that produces the planning artifact for the day. Output covers the prototype role plan (Maker, Stitcher, Writer, Asset Collector, Interviewer), prototype brief (what to build, fidelity bar, time allocation per role), canonical Five-Act Int

Pre-sprint diagnostic that determines whether a team should run a Design Sprint now, postpone it, or do prerequisite work first. Produces a Go / Conditional Go / Wait verdict with diagnosis, recommended preconditions, attendee list, customer recruiting plan, and pre-sprint activi

Day 2 (Tuesday) move of a Design Sprint that structures lightning demos and the four-step independent solution sketch protocol (Notes, Ideas, Crazy 8s, Solution Sketch). Each team member produces one solution sketch individually; the skill orchestrates the day but does not author

Day 5 (Friday) sprint-closing move of a Design Sprint that produces the bundled Friday artifact covering per-customer interview observations, best quotes, scorecard grid (sprint questions by customers), observed patterns, hot takes from each team member, and the Decider summary (

Day 2 morning move of a Foundation Sprint. Forces generation of 3 to 7 candidate approaches as one-page summaries before the team converges on a top bet. Use after Day 1 is signed and before Magic Lenses on Day 2 afternoon. Enforces a minimum of 3 approaches to prevent first-idea

Day 1 morning move of a Foundation Sprint. Forces explicit team choices on target customer, important problem, team advantage, and competitors and alternatives. Produces a single coherent strategic frame that becomes the input to Day 1 afternoon Differentiation. Use after the spr

Pre-sprint brief that locks scope, the decision the sprint must unlock, team and role assignments, logistics, inputs to bring, and success criteria before Day 1 of a Foundation Sprint. Use after the readiness verdict is Go and before the sprint begins. Produces a one-page artifac

Day 1 afternoon move of a Foundation Sprint. Converts the morning's Basics frame into a defensible strategic position by scoring differentiator candidates against customer-perceived value, choosing two committed differentiators, plotting alternatives on a 2x2 chart, writing decis

Day 2 end capstone move of a Foundation Sprint. Compresses the sprint's full strategic frame into a single canonical sentence (the Founding Hypothesis) plus an assumption scorecard, why-we-believe, what-could-prove-us-wrong, and recommended next validation step. Use after Magic L

Day 2 afternoon move of a Foundation Sprint. Evaluates the candidate approach set through multiple lenses (4 classic plus at least 1 custom) to surface trade-offs, identify consistent winners and contradictions, and produce a top bet plus a backup plan. Use after Approach Options

Pre-sprint diagnostic that determines whether a team should run a Foundation Sprint now, postpone it, or do prerequisite work first. Produces a Go / Conditional Go / Wait verdict with diagnosis, recommended preconditions, attendee list, and pre-sprint activities. Use when a team

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 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