LLM Mart Basic

Post-install setup for foundry plugin. Run once after installing on a new machine, or after a plugin version upgrade to sync settings and symlinks. Merges statusLine, permissions.allow, enabledPlugins, and advisorModel into ~/.claude/settings.json; symlinks rules and TEAM_PROTOCO

Prepare release communication and check readiness. Main mode: notes with optional flags --changelog, --summary, --migration, --append (incremental: reruns the full pipeline scoped to newly-landed commits, integrating results into existing DRAFT.md/CHANGELOG.md/SUMMARY.md/MIGRATIO

OSS maintainer fast-close workflow for GitHub PRs. Three phases: (1) PR intelligence — reads full thread, linked issues, PR body to synthesize contribution motivation and classify every comment into action items; (2) conflict resolution — checks out PR branch (fork-aware via gh p

Multi-agent code review of GitHub Pull Requests (Python source, documentation (Markdown/RST), and CI/CD config PRs) covering architecture, tests, performance, docs, lint, security, and API design. TRIGGER when: user provides a GitHub PR number (e.g. 42, #42) and asks to review/au

Post-install setup for the oss plugin. Run once after installing on a new machine, or after a plugin version upgrade, to deliver this plugin's rules/*.md into ~/.claude/rules/ as namespaced symlinks. TRIGGER when: user installed or upgraded the oss plugin and its rules are not lo

Investigation-first debugging — gather evidence, form confirmed root-cause hypothesis, hand off to fix mode with diagnosis file. TRIGGER when: user reports a symptom or failing test with Python traceback, or asks to investigate a runtime/CI failure with reproducible evidence; phr

TDD-first feature development — crystallise API as a demo test, drive implementation to pass it, run quality stack and progressive review loop. TRIGGER when: user asks to build new functionality, add a capability, or implement a feature in a Python project; phrases: "add X", "imp

Reproduce-first bug resolution — capture bug in failing regression test, apply minimal fix, run quality stack and review loop. TRIGGER when: user reports a bug, regression, or unexpected behaviour in Python code with a traceback, failing test, or issue number; phrases: "fix this

Analysis-only planning — classify and scope a task without writing code; outputs a structured plan to .plans/active/. TRIGGER when: user wants to understand scope and risks before implementation; phrases: "plan this", "scope out X", "what would it take to Y", "analyse before we s

Test-first refactoring — audit coverage, add characterization tests, apply changes with safety net, run quality stack and review loop. TRIGGER when: user wants to restructure existing Python code without changing behaviour; phrases: "refactor X", "clean up Y", "extract Z", "restr

Multi-agent code review of local Python files, directories, or the current git diff covering architecture, tests, performance, docs, lint, security, and API design. Scope: Python source files in local working tree. Python-file-free targets (pure JS/TS/Go/Rust projects) are out of

Post-install setup for the develop plugin. Run once after installing on a new machine, or after a plugin version upgrade, to deliver this plugin's rules/*.md into ~/.claude/rules/ as namespaced symlinks. TRIGGER when: user installed or upgraded the develop plugin and its rules ar

Systematic ablation study runner. After research:run finds improvements, fortify identifies component candidates from git diff + diary, creates isolated git worktrees per ablation (main repo never modified), runs metric+guard in each worktree, ranks component importance, and opti

Research-supervisor review of program.md — validates experimental methodology (hypothesis clarity, measurement validity, control adequacy, scope, strategy fit), emits APPROVED / NEEDS-REVISION / BLOCKED verdict before expensive run loop.

Generate a Kaggle competition notebook as a Jupytext `# %%` Python script following the user's established ML research style: PTL for DNN training, best-fit tool selection, EDA→Baseline→Train→Inference pipeline with per-stage lens cells, small single-purpose cells each carrying a

Interactive wizard that scans the codebase, proposes a metric/guard/agent config, and writes a program.md run spec. Also runs cProfile on a file path to surface bottlenecks before prompting for optimization goal.

Post-run retrospective: reads .experiments/ JSONL, computes Wilcoxon significance, detects dead iterations, flags suspicious jumps, generates next-hypothesis queue for --hypothesis flag.

Sustained metric-improvement loop with atomic commits, auto-rollback, and experiment logging. Iterates with specialist agents, commits atomically, auto-rolls back on regression. Accepts a program.md file path. Supports --resume, --team, --colab, --codex, --researcher, --architect

Post-install setup for the research plugin. Run once after installing on a new machine, or after a plugin version upgrade, to deliver this plugin's rules/*.md into ~/.claude/rules/ as namespaced symlinks. TRIGGER when: user installed or upgraded the research plugin and its rules

Non-interactive end-to-end pipeline — auto-configure program.md (accept defaults), run judge+refine loop (up to 3 iterations), then run the campaign. Single command from goal to result.

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