LLM Mart Basic

Run a focused security pass on GitHub Actions workflows before merge so token misuse, dangerous permissions, and unpinned actions are caught early.

This ASE skill uses zizmor to audit GitHub Actions workflows and composite actions for security mistakes before they ship. An agent can scan local repos or remote GitHub repositories, flag risky permission scopes and unsafe workflow patterns, and return plain output, GitHub-nativ

Produce a license inventory for Go module dependencies before release, procurement review, or open-source due diligence.

Uses Lynis to run an on-host security audit and turn the findings into a prioritized hardening checklist for an agent or operator. Invoke it when a machine is about to become internet-facing, after base image changes, or whenever you need a quick read on hardening drift instead o

This skill uses OpenClaw's healthcheck workflow to inspect the host running the assistant, surface risky exposure, and turn the findings into a staged hardening plan. It is for operator-style audits with explicit approval gates, not a generic software listing or a replacement for

Use Deptry when an agent needs to verify that a Python project's declared dependencies still match the imports the code actually uses. The agent scans the codebase, flags unused direct dependencies, missing declarations, and transitive imports that only work by accident, then tur

Scan Python requirements and environments for known vulnerable or malicious packages before they move further through delivery or promotion workflows.

Check Python environments and requirements files for published vulnerabilities before shipping, upgrading, or approving dependency changes.

Inspect an SSH endpoint or config for outdated ciphers, key exchange choices, and hardening gaps before exposure or upgrades.

Use GEO SEO Claude when Claude Code should run repeatable AI-search and SEO audits with citability, crawler, schema, platform, and report workflows.

Use Agent QA's CLI and MCP server to author, validate, run, debug, and triage natural-language web and mobile regression tests with persistent test memory and reviewable run evidence.

Use smartcrop when an agent needs to choose a sensible crop automatically instead of center-cropping every image. The workflow scores visual saliency, returns crop coordinates for a target aspect ratio, and hands those coordinates to an image pipeline that renders the final thumb

Auto-Editor is a command-line application that automatically edits video and audio by analyzing loudness, motion, and other signals to cut dead space. It exports to Premiere Pro, DaVinci Resolve, Final Cut Pro, ShotCut, and Kdenlive timelines.

Use Odigos to add OpenTelemetry tracing to Kubernetes or VM workloads without code changes, then route the traces to the observability backend an operator already uses.

Lint Nix expressions and automatically rewrite common anti-patterns before review or refactor work.

AutoGen is Microsoft's open-source framework for building multi-agent systems where AI agents converse with each other and humans to solve tasks, with support for tool use and human-in-the-loop workflows.

Lets agents operate Google NotebookLM/Gemini Notebook through a Python API, CLI, skill, MCP server, or REST server to create notebooks, add sources, ask cited questions, generate artifacts, and download exports.

Operate Lark and Feishu work objects from one agent-ready CLI instead of stitching together separate APIs and browser flows.

Use ARIS to run Markdown-based agent skills for literature review, idea discovery, cross-model critique, experiment planning, and paper-writing support.

Use NotebookLM through MCP or a local REST API to run cited Q&A, generate Studio artifacts, and manage high-volume research batches.

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.

Use MCP Inspector to connect to local or remote servers, inspect capabilities, call tools, read resources, test prompts, and diagnose failures before release.

Build an MCP server in TypeScript with focused tools, validated schemas, local and remote transports, Inspector tests, and production security controls.

Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only.

Lightweight Q&A about the project — answer from context and return, no routing, no state change.

Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report.

Sanctioned lane for non-behavioral work — docs-only edits, dependency bumps, reverts. Type-scaled gates; no TDD demanded of prose.

Clean up an already-merged local branch after proving containment. Confirm each discard and preserve unique work.

Show the codeArbiter command catalog — the public command list and what each routes to.

Create a verified local Git commit when committing changes is requested. Not for explaining commit history, drafting a message only, or postponing a commit. Applies every commit gate and never implies a push or PR.

Stop everything and surface a rule conflict — persona vs. docs vs. code. Present both sides and the conflict-hierarchy level; the user resolves. No silent reconciliation.

Audit stale provenance-tracked docs on request. Report first; re-scout or re-baseline only for selected docs.

Build project context from an existing codebase through isolated scouts, resolve gaps, and preserve initialization gates.

Investigate an unexplained defect or unexpected behavior without changing application code. Use for root-cause diagnosis and an evidence-backed handoff. A no-action close records a board note. Not for implementing a known fix, new features, or explanation-only questions.

Develop greenfield project context through a layered interview, preserve decisions, and initialize only after the required gates.

Verify the active host install, package, command ownership, enforcement, and harmless live-fire probe. Read-only.

Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. The one entry to implementation.

Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates.

Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store.

Read-only 3-metric governance glance — override rate, small-lane rate, sprint low-confidence ratio — each with a trend arrow vs. the prior 20-commit window.

Sanctioned, logged bypass of a gate or hard rule — one audit line, then proceed.

Open a PR or finish branch disposition; route CI watching and post-merge cleanup to their owners. Merge and discard need explicit authority.

Zero-onboarding, read-only dry-run of the reviewer fleet against the current uncommitted diff. Predicts reviewers, runs the state-free secret scan, writes nothing.

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