LLM Mart Basic

Grill the user about a requirement, decision, or idea before implementation, then produce an actionable planning report without writing code. Use when the user wants to clarify requirements, stress-test an idea, compare approaches, or plan before coding.

Localization scope and AI-translation execution for Apple-platform Apps on `Localizable.xcstrings` — default locale set, source / primary language rule, per-locale review gotchas, completeness gates. Use when deciding which locales to ship at project setup; when adding or refresh

Use when preparing an App Store submission, reading an App Review rejection or Resolution Center message citing a guideline number (2.1, 2.3.x, 3.1.1, 4.3, 5.1.1, 5.1.2), or a privacy-manifest upload email (ITMS-91061 / ITMS-91056, missing required-reason API), or auditing an ads

Default minimum deployment target for Apple-platform Swift Apps — iOS 26 / macOS 26 on the Xcode 26 toolchain (Swift 6 language mode) — and how to deviate down (iOS 18 / 17) or up. Use when starting a new Apple-platform project, writing the Package.swift `platforms:` list, decidi

Use when a repo goes public or open-sources, when a CloudKit server-to-server PEM, ASC API `.p8`, APNs key, signing `.p12`, or provisioning profile first enters the pipeline, or when asked how to prevent or respond to a secret leak (gitleaks, lefthook, GitHub Secret Scanning, `gi

Choose analytics and metrics sources for a solo / small-team Apple app and decide whether a third-party tracking SDK is justified. Use when picking an analytics SDK; when asked "should I add Firebase / Mixpanel / Amplitude / TelemetryDeck"; when asked what App Store Connect Analy

Use when wiring a value that ships in the binary but must stay out of public-repo diffs until launch (AdMob `GADApplicationIdentifier` / banner unit ID, a third-party SDK app key) into an Apple build via xcconfig, Info.plist `$()` substitution and a guarded `Bundle.main` read, in

Committed `.ckdb` as the CloudKit schema source of truth, with `xcrun cktool` export / validate / import against Development and Production promotion kept as a Console-only gate. Use when a CloudKit-backed persistence layer adds or edits a record type, field, or index; before any

Wire and debug launch-the-app XCUITest E2E tests in a Tuist project: a native `.uiTests` target needs its own scheme with `testAction: .targets([...])`, not `.xctestplan` membership; a name that does not collide with an SPM UITests package target; window-frame-anchored clicks for

Audit an iOS/iPadOS app's live behavior on a booted Simulator by driving it with `idb` (accessibility tree, taps, screenshots) to find bugs a fixed-frame snapshot cannot show — navigation and modal flows, back-stack, completion screens, safe-area / Dynamic Island clipping, offlin

Implement and audit VoiceOver (`accessibilityLabel` / `Value` / `Hint`, traits, `accessibilityElement(children:)`, `AccessibilityNotification`), Dynamic Type (text styles, caps, AX5), 44pt touch targets, and Reduce Motion / Transparency for SwiftUI and UIKit, with a WCAG 2.2 mapp

Generate a single-file HTML iOS design mockup from a written spec (PRD / requirements / user stories) — a designer-style user-flow canvas: iPhone frames, SVG navigation arrows, a design-tokens panel. Use when asked to "turn this spec into a mockup", "show me the screens", "visual

Measure and fix iOS/macOS performance with Instruments (Time Profiler, Allocations, Hangs, App Launch), `xctrace` in CI, `OSSignposter`, MetricKit field telemetry (`MXMetricManager`, `MXHangDiagnostic`), `XCTMetric` baselines, launch time, memory footprint, binary size, and crash

Use when a build must reach TestFlight without Xcode Cloud (quota, outage, CI not wired yet), or when a local `xcodebuild archive` / `-exportArchive -exportOptionsPlist` / `xcrun altool --upload-package` command fails — `ExportOptions.plist` keys (`method`, `destination`, `teamID

Use when pinning binary CLI / build tools (swiftlint, xcbeautify, gitleaks, lefthook) with mise so dev machines and CI share one `.mise.toml` — choosing mise vs asdf / Homebrew / manual, writing `.mise.toml` (`aqua:` / `github:` backends, `os = ["macos"]` guards), running `mise t

Use when adding, upgrading, or auditing a third-party monetization SDK (AdMob / Google Mobile Ads incl. UMP consent; the same contract applies to any other ad or subscription SDK), or when a PR adds `import GoogleMobileAds` outside the single live-bridge file, breaks `canImport`

Set up logging for an Apple-platform Swift app with `os.Logger` and decide its `subsystem` / `category` naming and `privacy:` interpolation. Use when choosing a logging library (`os.Logger` vs swift-log `import Logging` vs CocoaLumberjack); when writing the first `Logger(subsyste

Default StoreKit 2 architecture for a single non-consumable IAP (Remove Ads, Pro Unlock): `StoreKitBridge` isolates `import StoreKit` to one Live file; launch-time `Transaction.updates`; `Transaction.currentEntitlements` for unlock state; `finish()` timing; `AppStore.sync()` rest

Design injectable seams so Swift services can be swapped for fakes in tests. Use when a type reaches for `URLSession.shared`, `Date()`, `UUID()`, `random(in:)` or a singleton; when asked "how do I inject CloudKit / network / clock" or "should this be a singleton"; when choosing c

Default test stack for new Apple-platform Swift projects — Swift Testing (`@Test` / `#expect`, no XCTest), pointfreeco/swift-snapshot-testing with baselines in git, CI policy for fakes (no live CKContainer / GKLocalPlayer / network in tests). Use when creating the first test targ

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.