LLM Mart Basic

Delegates work to a subagent or spawned session by writing only the task, while a PreToolUse hook pages the parent transcript through Jev and appends the chunks that task needs. Use before writing any Agent tool prompt or create_session prompt, and when asked to delegate this, ha

Distill Opus-level reasoning into optimized instructions for Haiku 4.5 (and Sonnet). Generates explicit, procedural prompts with n-shot examples that maximize smaller model performance on a given task. Use when user says "down-skill", "distill for Haiku", "optimize for Haiku", "m

Build and audit deterministic verification gates — a check that blocks a pipeline and can be shown to go red. Use when writing a calibration gate, CI check, validation script or pre-publication check for a numeric or empirical result; when a plausible-but-wrong value would surviv

Break out of a locked problem frame by picking one disciplined move — reframe, provocation (Po), random stimulus, SCAMPER, inversion, structured analogy, constraint play, or family traversal — and committing to it before evaluating. Use when stuck, when options feel narrow or obv

Install and drive Google's Antigravity CLI (`agy`) as a non-interactive sub-agent. Use when orchestrating agy, running Antigravity agents from a script or sandbox, delegating a task to Google's agent harness, or wanting a Gemini-backed peer agent alongside Claude.

Invokes Google Gemini models for structured outputs, image generation, text-to-speech narration, multi-modal tasks, and Google-specific features. Use when users request Gemini, image generation, Gemini TTS or a synthesized voice, structured JSON output, Google API integration, or

Analyzes an AI/ML publication — paper, preprint, article, technical blog post — and extracts what an enterprise AI engineer should do about it. Use when someone supplies a URL or document on RAG, embeddings, fine-tuning, prompt engineering, agents, or LLM deployment and asks "rev

Exhaustive problem space exploration using the MIT Synthetic Neurobiology "tiling tree" method. Partitions a problem into MECE (Mutually Exclusive, Collectively Exhaustive) subsets recursively via parallel subagents, then evaluates leaf ideas against specified criteria. Use when

Check that a document's claims about code are actually true by reading the prose, the code, and the tests and reporting (or fixing) where they disagree. Use whenever the user wants to verify a README, guide, spec, or docstring still matches the code; whenever they mention documen

Pre-change blast-radius report for a symbol or file. Walks tree-sitting references, augments with a plain-text scan over non-parsed files (configs, plain docs), and clusters affected sites by feature (`_FEATURES.md`) or top-level package. Use when about to refactor, rename, or de

Find tests that enumerate a domain by copying it, and declare the invariants a codebase depends on. Reports where a parametrize list, for-loop, or it.each iterates a hand-written subset of a dict/set/tuple/Enum that exists in the source, and names the members nothing covers. Use

First-encounter orientation on a repository nobody here has worked in yet. Runs a fixed five-step workflow — venv setup, tarball fetch, tree-sitting structural scan, featuring synthesis, then reasoning over the two — and yields an account of what the repo contains and how it is a

Generate hierarchical _FEATURES.md files that describe what a codebase DOES from a user/consumer perspective, anchored to source symbols via tree-sitting. Supports large complex codebases through feature-driven decomposition into sub-feature files. Uses a multi-pass synthesis: or

DEPRECATED — superseded by tree-sitting. This skill generated persistent _MAP.md files; tree-sitting does the same AST extraction at runtime (~700ms for 250 files) with no artifact to write, commit, or keep in sync. Use tree-sitting for "map this codebase", "explore repo", "under

Interactive codebase orientation for a HUMAN who wants to learn the code. Runs the same tree-sitting + featuring pipeline as exploring-codebases but synthesizes it into guided exercises and an HTML teaching artifact rather than an analysis document. Use for "orient me to this rep

Apply semi-formal certificate reasoning to code analysis — patch verification, fault localization, patch equivalence. Use when reviewing patches, hunting bugs across scopes, comparing fixes, or when code reasoning requires tracing execution across files/modules. Triggers on code

Binding-resolved Python symbol queries via pyright — every true caller (--refs), the real definition (--def), or an inferred signature (--hover) of a .py symbol, excluding the same-named false positives text search cannot tell apart. Use when a task needs ALL callers or users of

In-process semantic search over text files or in-memory strings, using Gemini embeddings via the CF AI Gateway. Use when user wants fuzzy/conceptual search where exact-keyword grep would miss — "sessions discussing regulatory constraints", "code about retry logic", "notes mention

Symbol-level navigation of a local checkout using tree-sitter ASTs. Answers where a symbol is defined, what lines it spans, which symbols a file exposes, what a directory holds, and where a name is referenced — every answer carries exact line ranges to feed straight into a scoped

Create interactive data visualizations using Vega-Lite declarative JSON grammar. Supports 20+ chart types (bar, line, scatter, histogram, boxplot, grouped/stacked variations, etc.) via templates and programmatic builders. Use when users upload data for charting, request specific

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