LLM Mart Basic

View and configure settings for coding agents (Claude Code, Codex CLI, OpenCode, and others). Covers JSON settings for Claude Code, TOML for Codex CLI, and JSON/JSONC for OpenCode, including permissions, sandbox, model selection, profiles, feature flags, providers, hooks, subagen

Maintain a project thesaurus (domain glossary) following DDD ubiquitous language principles. Use PROACTIVELY when naming anything: variables, functions, classes, modules, database fields, API endpoints, events, files, or directories. Also use when the user asks to "create thesaur

Use when testing Windows 11 desktop apps (WinForms/WPF/UWP) via UFO UIA/Win32 automation MCP. Triggers on "test this Windows app", "QA the app", "run smoke test", "click the button", "fill the form", "check the UI", "Windows automation", "UFO QA", "verify the dialog", or any Wind

Token-isolated deep research agent for academic papers. Orchestrates Exa MCP (neural multi-source discovery), allenai's semantic-scholar-lookup skill (fast metadata + forward citations via asta CLI), and the semantic-scholar-deep skill (references, recommendations, batch, citatio

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 190,000+ scientists worldwide. 165 ready-to-use validated skills plus 1…

Work with a local My Wiki knowledge base, Dashboard, and knowledge graph. Also use for explicitly requested remote/public knowledge access, including “远程知识库”, “远程服务”, “公网知识库”, and “公网服务”.

Use when touching retiring old logic, collapsing duplicate owners, removing fallbacks, or schema/persistence/source-of-truth boundaries; identify opportunities automatically; destructive execution requires explicit confirmation.

Use when defining ambiguous or high-complexity new features, product behavior, UI/component design, architecture choices, contract changes, or when grilling/pressure-testing a plan or design. Routine small requests stay on the fast path.

Use when the user asks for caveman mode, fewer tokens, brief responses, compressed communication, or otherwise explicitly requests a much shorter answer.

Use when facing 2+ independent tasks without a written plan, with no shared state or sequential dependencies, where parallel delegation beats inline cost; otherwise inline. Planned tasks use subagent-driven-development.

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

Use when executing a written implementation plan across sessions or with review checkpoints. Small or single-slice plans stay inline. For same-session independent tasks, use subagent-driven-development instead.

Use when verified work needs integration or cleanup of an existing task-created branch/worktree, or the user explicitly requests merge, PR, or branch lifecycle handling.

Use when asked for first-principles or Occam's-razor review, or when high-risk decisions involve competing constraints, fallback growth, duplicate owners, or architecture direction risk. Ordinary bug fixes stay on the fast path.

Use when the user explicitly sets an Aegis goal with /aegis-goal, Aegis goal:, or asks to define goal, success evidence, stop condition, or task boundaries before work.

Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion.

Use when receiving code review feedback before implementing suggestions, especially when feedback is unclear, risky, disputed, or technically questionable.

Use when the user asks to create, write, update, amend, supersede, or evaluate an ADR, architecture decision record, durable architecture decision, decision log, or baseline sync after architecture-changing work.

Use when requesting independent code review, after implementation slices, before merging high-risk work, or when verification exposes evidence, baseline, architecture, compatibility, or retirement uncertainty.

Use when executing a written implementation plan with independent tasks in the current session where delegation beats inline coordination cost; otherwise inline. Ad-hoc 2+ tasks without a plan use dispatching-parallel-agents.

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.

{{SKILL_ENTRY:refactor}}

{{SKILL_ENTRY:release}}

Review a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub PR.

Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or {{CMD:feature}}.

Autonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logged. Hard gates remain true stops.

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.

Wire codeArbiter's statusline into ~/.claude/settings.json, or remove it.

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.

{{SKILL_ENTRY:security-architecture}}

{{SKILL_ENTRY:tribunal}}

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

Copy a file OUT of a running sandbox box to the host — host-initiated egress only (docker cp). The reverse, a host→container bind, is impossible by construction.

Tear down a sandbox box — remove its container and named volume. --keep-volume leaves the volume; with no id, prune reclaims any leaked ca.sandbox=1-labeled object. Cached images are retained.

Run a single command inside a running sandbox box and capture a JSON result — exitCode, separate stdout/stderr, and a truncated flag past the byte cap. The scriptable exec seam.

Open an interactive shell inside a running sandbox box at /work/repo. Read-only root, non-root user, no host-FS access — explore the untrusted code interactively, then exit.

Pull an untrusted repo into an ephemeral, host-FS-isolated Docker container — clone into a named volume, build a dep-cached image, run under structural isolation. Network defaults to offline. Requires Docker and nixpacks.

Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.

Inspect ADR health read-only; optionally select one ADR with --adr N.

Record user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.

Atom Agent, Open-Source Governed AI Agent Platform for Self-Hosted Automation

The agent engineering intelligence harness, optimized tools, memory system, subagents and mixture of models packages ⚚

Sesori iOS/Android app and the Sesori Bridge CLI — drive Claude, Codex, OpenCode, Cursor, Pi, OMP, Hermes coding sessions from your phone

🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.

Use ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers — OAuth login in the web UI, no API keys

Latitude is the open-source AI monitoring platform.

Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

Official Model Studio CLI（阿里云百炼 CLI）built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.

Curated DeepSeek Harness (DSH) plugins, extensions, tools, skills, clients, runtimes, integrations, and verified references — English and Chinese.

Turn papers, code, and docs into presentation-ready, natively editable PPTX in Codex / Claude Code. Native charts and equations, speaker notes, click-build anim…

Grix : Work with agents like talking to people.

Local First Ai Agent. Optimized for Local Ai models. Long context window. Proper tools callings. Runs privately on your device.

Model Context Protocol server that integrates AgentQL's data extraction capabilities.

AI that ships your tickets.

Metadata-driven CLI for AI Agent Bots — 48 operations across 7 domains, structured JSON envelope I/O, zero interactive prompts.

An open-source, extensible, self-hosted agent workspace with multi-runtime support for Codex, Claude Code, and more, plus reusable local apps for custom interfa…

Open-source Windows desktop client and GUI for DeepSeek Harness — zero-setup installer with Codex, plugins, skills, SSH, mobile remote access, and 11 skins.

The open-source AI workbench for scientific research

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

A Fully free agentic browser driver for AI , few tools, full control, real stealth, top-tier token efficiency.