LLM Mart Basic

Daily repo hygiene — review the day's repo state, then perform the cleanups under per-action confirmation. Fast-forward only, never destructive without a yes.

Show the project's current state at a glance — stage, open tasks, open questions, overrides since the last checkpoint, current branch. Read-only.

The sanctioned task-board mutator — add a queued task, start one (flips to in-progress and stamps the date, minting a dotted ID on pick-up), or mark an in-progress task done. The only blessed write to open-tasks.md.

Opt-in lightweight STRIDE pass for a sensitive feature before implementation. Not a routine gate — invoke it when a change warrants security thought.

Deep, rarely-convened whole-codebase audit — eleven specialist lenses, a resumable on-disk audit log, findings filed as GitHub issues on approval. Expensive; estimates cost and STOPs before running. Never a required gate.

Watch a PR's CI to completion — diagnose on red, notify and offer the merge on green. Never auto-merges.

Imported from arbiterforge/codearbiter/core/surface/agents/INDEX.md.

Read-only checkpoint reviewer. Surfaces drift between the codebase and accepted ADRs in .codearbiter/decisions/. Informational — never blocks.

Reviews authentication, cryptography, key handling, and secrets against {{PROJECT_DIR}}/.codearbiter/security-controls.md. Hard blocks on banned primitives, exposed secrets, disabled TLS verification, and shell injection. Read-only checkpoint reviewer.

Use when writing or modifying backend/server-side code. Owns the TDD workflow, input validation, framework conventions, and ORM usage. MUST write failing tests before implementation code. Reads tech stack from {{PROJECT_DIR}}/.codearbiter/tech-stack.md.

Composes the finding-triage report and decision-challenger output into a dated checkpoint document under .codearbiter/checkpoints/YYYY-MM-DD.md. Aggregator, not a blocker.

Dispatched by the tdd skill (Phase 4) to audit test coverage against TDD obligations. Identifies untested source files, coverage below the maturity threshold, and logical test gaps.

Adversarial red-team reviewer of ADRs. Builds the strongest case against each decision, names load-bearing assumptions, assigns confidence 1–5, and surfaces evidence that would prove a decision wrong. Read-only. Dispatched optionally by decision-variance. Reads ADRs from .codearb

Dispatched when package.json, lock files, or container base images change. Verifies license, provenance, maintenance signal, and supply-chain posture against .codearbiter/security-controls.md and .codearbiter/tech-stack.md before merge.

Reviews generated, user-facing visual or formatted output (UI, reports, slides, charts, diagrams, CLI output) against the anti-slop-design reference. Read-only; surfaces design-slop findings. Dispatched by frontend-author on UI changes. Tier 2 document producers (/pr, release) ap

Post-processes all checkpoint reviewer reports — consolidates findings, classifies each by severity and whether it blocks the current change. Sequential. Produces a unified triage report for the checkpoint-aggregator. Reads project state from .codearbiter/.

Use when writing or modifying frontend/UI code. Owns the TDD workflow, component conventions, state management, and UI security. MUST write failing tests before implementation code. Reads tech stack from {{PROJECT_DIR}}/.codearbiter/tech-stack.md.

INTERNAL SMARTS analyst dispatched by the decision-variance skill. Produces a SMARTS analysis and recommendation for one (artifact-position, scaffold-evidence) pair. Never decides — the user decides. Never dispatch directly.

Use when writing or modifying IaC, containers, CI/CD manifests, or deployment configuration. Reads tech stack and security boundaries from {{PROJECT_DIR}}/.codearbiter/.

Dispatched by the tribunal deep-audit lane's Phase 1, on a large/sprawling repo, to offload dependency/integration-surface mapping out of the orchestrator's retained context. Read-only extractor, not a judge — reports facts, files no findings.

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.

Guided component creation with proper patterns

Review existing UI for issues and improvements

Initialize a design system with tokens

Generate unit tests for Python, JavaScript/TypeScript, and React code with mocks, edge cases, and coverage gap analysis

Turn a recorded product demo into a prioritized backlog with timestamped evidence.

Turn one screen recording of a bug into an evidence-backed GitHub issue draft (quote, frames, OCR identifiers, wall-clock; silent recordings work too).

Walk a recording's remarks against system logs using wall-clock timestamps.

Turn a recorded meeting (audio is enough) into action items, decisions, and open questions with timestamps.

Turn a recorded workshop or design walkthrough into a structured spec with quoted decisions and open questions.

Turn a narrated screencast into precise, evidence-backed findings JSON (bug / feature / question routing with frame evidence).

Generate and enforce policy gates for AI coding agents (Copilot, Claude Code) — real-time session hooks that deny protected-path edits and dangerous commands, plus a merge-time backstop for anything that bypasses them. Use when asked to "govern AI agents", "block AI from touching secrets", "add an AI policy gate", or "why did the AI agent hook not fire".

Show the active planning-with-files plan (id, mode, attestation, current phase, phase counts)

Start planning-with-files (task_plan.md, findings.md, progress.md); flags --gated, --autonomous, --template analytics, then an optional plan name

Run a paid-ads (ROAS) workflow: audience segments, account structure, ad creative, experiment design, pre-launch signal QA + the account-audit gate, measurement, and attribution. Not sure? Use /aaron-marketing:auto.

Natural-language front door to the marketing pack (narrative/TALE, SEO/GEO/SITE, social/ECHO, email/SEND, Paid Ads/ROAS, influencer/STAR, launch/RAMP). Use when a marketing goal is open-ended or spans disciplines, when it is unclear which skill fits, or for requests like 'help with our marketing', 'grow our traffic', 'plan our launch', 'what should we post', 'is our messaging landing' — it infers the discipline and runs the smallest useful workflow. Add --deep for exhaustive, maximum-rigor, or stress-test runs.

Run an email-marketing (SEND) workflow: deliverability/consent setup, segmentation, email creative, lifecycle flows, newsletter monetization, send-testing, and the email-quality audit gate. Not sure? Use /aaron-marketing:auto.

Run an influencer-marketing (STAR) workflow: audience & creator scouting, campaign targeting, briefs, outreach, amplification, and ROI reporting. Not sure? Use /aaron-marketing:auto.

Run a product-launch (RAMP) workflow: positioning and launch tiering, window/early-access design, message house and asset kits, the launch-readiness gate with a T-1 go/no-go, launch-day execution, and the post-launch prove loop. Not sure? Use /aaron-marketing:auto.

Run a brand-narrative & messaging (TALE) workflow: trace the current message and positioning truth, architect the durable message house/voice/story canon, land it consistently across every surface, and evaluate resonance with tests and drift monitoring. Not sure? Use /aaron-marketing:auto.

SEO/GEO end-to-end along the SITE loop: survey demand and competitors, implement content, tune quality/tech/on-page, and evaluate authority/rankings/reports/memory (--phase survey|implement|tune|evaluate). Not sure? Use /aaron-marketing:auto.

Open-source, self-hosted AI media server. One server replaces your entire media stack, with a web app, native iPhone app, and an AI agent that gets things done.…

A curated list of tools built for Jev — TypeSafe AI's System One model for typed decisions.

🦦 Crayotter: A Multimodal AI-Agent for Video-Editing, Video-Composing, and Video Production. Powered by Multimodal LLMs for autonomous Text-to-Video agentic fr…

Webextension tool for Odoo

基于多模态视觉感知与 LLM Agent 的 macOS 微信自动化框架 | Visual RPA for WeChat

The operational superset of Pi Coding Agent — everything Pi, plus observability, governance, recovery, evaluation and multi-agent orchestration. Pi Coding Agent…

Metrik 可以集中查看本机多个 Agent 的配额余量和 Token 消耗，目前支持 ChatGPT、Claude、GLM、Kimi 等主流 AI 服务。

An AI agent with a real self — soul she wrote, desires that drive her, a heartbeat for autonomous action, dreams she processes when you're away. Capability supe…

Production-ready open source terminal coding agent with readable, layered code: permission rules, OS sandboxing, MCP, skills, sub-agents, and Anthropic, OpenAI-…

Answer me with HTML — an agent skill that answers hard questions with a one-page HTML you can actually read. 让 AI Agent 用一页 HTML 回答复杂问题。

Prompt packs that make any AI agent a LaTeX expert — fix errors, polish writing, format for venues, read papers, recover source

Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit) for divergent ideat…

Claude Code + OpenClaw + Codex + WorkBuddy 中文教程 | 50篇完整教程 + 1张速查卡 | 80万+内容量 | 1500+实操示例 | AI Coding / Agent 四线学习路径（编程+助手+Agent+办公）

SmartLabelBench 2026: LLM-Powered Auto Annotation and Dataset Builder for Everything

从零开始玩转OpenClaw：最全面的中文教程，涵盖安装、配置、实战案例和避坑指南（github版）