LLM Mart Basic

Imported from arbiterforge/codearbiter/site/src/curated/agents/tribunal-lens-reviewer.md.

Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth

Release moi-computer to npm — verify locally, hand off to the gated GitHub Actions workflow, then verify the published package. Defaults to a `next` preview; pass `stable` for a `latest` release. Use when the user asks to publish, release, ship a version, or cut a dev preview.

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a compon

The moi workspace — the web UI the user chats from, extended with agent-authored applets (widgets, views) plus theme & config. Read this FIRST when a message carries a hidden moi-context envelope or the user uses moi vocab such as workspace, applet, widget, view, scratchpad, dash

Embed screenshots, images, diagrams, GIFs, and screen recordings in GitHub PRs and issues — or stage them ahead of a PR, collect them into one attachments comment, or get a durable public link to share a visual with a person. Use this whenever a visual needs to end up in a PR des

Bake hand-drawn boxes, arrows, labels, freeform strokes, and redactions onto a screenshot so a PR reviewer or teammate sees exactly what changed and where to look, instead of reading a caption and hunting for it. Use this whenever a screenshot needs a callout — "point at the new

Reference for the uploads CLI and its stdio/hosted MCP tools — exact flags, keys, and contracts for put and attach, screenshot capture, stable PR/issue keys, the managed attachments comment, metadata and search, galleries, config defaults, login/doctor, and output formats. Use wh

Write Persian web copy (blog articles, product descriptions, landing pages, category text, microcopy, meta titles and descriptions) using Cursor workers, so the writing runs on the Cursor subscription's quota instead of Claude's. Use when the user asks for Persian content for a s

Delegate a coding or research task to the Cursor CLI (cursor-agent) so it runs on the Cursor subscription's quota instead of Claude's, with Claude still orchestrating. Use when the user says "delegate to cursor", "run this with cursor-agent", "offload to cursor", "spend the curso

Orchestrate a fleet of Cursor CLI (cursor-agent) workers to execute a large or multi-part job, while Claude does the architecture, UX/UI decisions, decomposition, review, and integration. Use when the user says "orchestrate with cursor", "build this with a cursor fleet", "fan out

Deep-clean and simplify a whole repo or codebase, then leave guardrails so it stays clean. Delete dead surfaces, gitignore build artifacts, relocate dev docs, notes, clones and dumps to the project's workspace repo (the assistant-dev home base), split oversized files and function

Give a repo its own rules at both layers, and put each rule at the cheapest layer that holds it. The told layer is what a project's workspace tells a model before it writes, so it establishes where a session starts, which repo each kind of file belongs in, how the gate is run, th

Generate a GitLab CI/CD pipeline and Helm chart that builds the current project with kaniko, pushes to the GitLab Container Registry, and deploys to a Kubernetes namespace via a kubeconfig CI variable. Use when the user asks to set up CI/CD, create a GitLab pipeline, write a Helm

Right-size Kubernetes pod CPU/memory requests from real Prometheus usage data (per-pod p95 CPU, p98 memory over 7 days), compute how many nodes the cluster needs, and tune KEDA queue-based autoscaling. Use when the user asks to rightsize workloads, fix over/under-provisioned requ

Deep OWASP reference for security reviews and secure implementation. Covers OWASP Top 10:2025, ASVS 5.0 levels, secure code patterns (injection, auth, error handling, fail-closed), language-specific security quirks for 20 languages, OWASP LLM Top 10 (2025), and Agentic AI securit

Apply a baseline of secure-coding standards to code being written or reviewed. Covers auth, secrets management, input validation, injection prevention, password hashing, PII handling, dependency hygiene, rate limiting, CORS, security headers, HTTPS, error/logging discipline, and

Export a reply or chat card as a standalone styled HTML report file, in the exact readable card template (Persian RTL with Vazirmatn, or English LTR with Inter). Use ONLY when the user explicitly asks to save, export, file, or extend THE CURRENT widget/card ("همین کارت رو ذخیره ک

Turn an answer into a light visual (flowchart, timeline, comparison, architecture sketch), in any language. Trigger ONLY when the user explicitly asks to see something visual, e.g. "show me", "visualize this", "show it as a diagram", "draw it", "با شکل نشون بده", "شماتیکش رو بکش"

The way into learnable and the way back. If a course already exists here it continues from exactly where the learner stopped, next lesson, next chapter, no re-planning. If nothing exists yet it asks whether to measure their level first or go straight to building a course. Use whe

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