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.

Plural alias for task status, pause, prompts, recovery, and ignore

Verify that the autorun plugin command surface is loaded

Tmux session management - create, list, cleanup isolated sessions, short for /ar:tmux

Tmux session management - create, list, cleanup isolated sessions

CLI testing in isolated tmux sessions, short for /ar:ttest

CLI testing in isolated tmux sessions

Graceful stop - finish current task then stop (short for /ar:stop)

Set AutoFile policy to ALLOW — permit creation of new files without justification

Refresh git commit guidelines before staging changes

Set AutoFile policy to FIND — restrict edits to existing files only

Start an autorun task with three-stage verification (initial → critical review → final verification)

Refresh the universal system design philosophy before designing or reviewing code

Show the current AutoFile policy and any active autorun state

Extract text from PDF files or directories to markdown

Trigger: `/ship` or "ship it" or "deploy to production"

Suppress 5-question enforcement for rapid sessions

Check a Dutch address for KPN outages and report what connectivity is available there

Find the KPN business-mobile contract for a lost or stolen phone and block its SIM after confirmation

Run the SkillOpt-Sleep cycle with the handoff backend — no API subprocess; this session answers the engine's model calls via prompt/answer files, in isolated fresh-context subagents

Run or manage the SkillOpt-Sleep self-evolution cycle (review past sessions, replay tasks through a selected backend, consolidate validated memory + skills, or schedule nightly runs)

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