LLM Mart Basic

Run one caller-supplied Codex command non-interactively and capture evidence. Triggers: "run Codex headless", "capture Codex evidence".

Gather independent views on a high-stakes judgment. Not for one-judge plan challenge; that is premortem. Triggers: "council", "multi-judge review", "independent perspectives".

Compile or lint a persistent Mayor-style goal prompt that ratchets a bead graph through bounded RPI experiments toward one larger outcome. Triggers: "craft a goal prompt", "mayor goal", "goal-runner prompt", "lint this goal", "is this goal safe". (Shaping one experiment's intent

Generate and validate repo docs, READMEs, and OSS doc packs. Triggers: "doc", "generate and validate repo docs", "doc skill".

Load the AgentOps language and bounded-context contracts when a term needs precise meaning. Triggers: "define this domain term", "check the bounded context".

Generate evidenced opportunities or challenge an idea with sealed perspectives. Triggers: "idea genie", "what should we build", "challenge this idea", "compare proposals".

Execute one bounded RED to GREEN experiment from bead or caller intent; return derived subject identity and check facts. Triggers: "implement", "implement this bead", "run the experiment". Full plan-to-validation requests route to rpi.

Shape or refine the existing bead or caller intent without a second planning artifact. Triggers: "plan", "discover and plan", "shape this goal", "review write scope", "check scope boundaries", "scope this change".

Optionally test a retrospective causal question against durable verdict evidence. Triggers: "postmortem", "causal retrospective", "test a retrospective hypothesis".

Compare a claimed state with observable repository evidence and report concrete gaps. Requires a claim or expected state to test. Triggers: "reality check", "is this claim actually done", "compare claim to repo".

Execute one behavior-preserving structural transformation and report evidence. Triggers: "refactor this", "simplify without changing behavior".

Answer one bounded question, cited. Not for dissecting a codebase; that is codebase-recon or reverse-engineer. Triggers: "research", "investigate this question", "find evidence".

Inventory an authorized repo, binary, or product. Not for tracing your own repo; that is codebase-recon. Triggers: "reverse-engineer X", "tear down Y", "what should we steal from Z", "evaluate competitor/upstream", "should we fork/adopt/build-native".

Coordinate one RPI traversal: one bounded Plan and Implement experiment, then fresh Validate and a bounded repair phase to convergence. Triggers: "run rpi", "run one traversal", "execute this plan", orchestration or worker delegation that implements changes.

Run authorized repository security scans for vulnerabilities, dependency risk, secrets, and binary policy. Triggers: "security", "run repository security scans for", "security skill".

Create a metadata-complete AgentOps skill source package, regenerate its derived projections, and check or repair structural hygiene in skill packages. Triggers: "create a skill", "scaffold skill", "absorb external skill", "new skill", "heal skill", "repair skill hygiene", "audit

Author and tier behavioral probes for a skill, including seeded-defect probes that escape ceiling saturation. Triggers: "measure this skill", "the probe came back INERT", "the control arm aces it", "harden this scenario", "is this skill actually doing anything".

Operate a caller-selected Gas City 1.4 with upstream registry packs and native run-centered surfaces while keeping GC runtime state out of AgentOps verdicts. Triggers: "using gc", "gas city", "drive the mayor", "dispatch through gc".

Freshly judge a finished change against its acceptance: PASS, FAIL, or NOT_PROVEN. Not for claim-vs-tree checks; that is reality-check. Triggers: "validate", "is this proven", "check this change", "cross-model review".

Imported from boshu2/agentops/skills/_fixtures/bad-skill.

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.

`crabbox shard` forks a [checkpoint](checkpoint.md) into `--count` leases

`crabbox share` grants other people access to an existing lease through the

`crabbox ssh` resolves a lease and prints a ready-to-run `ssh` command for it.

`crabbox status` prints the current state of a lease: its slug, provider,

`crabbox stop` ends a single lease. For coordinator-backed and direct cloud

`crabbox sync-plan` prints the local sync manifest and its size hotspots

`crabbox tunnel` opens one foreground SSH local port-forward to a resolved

`crabbox unshare` removes sharing rules from a coordinator-backed lease. It is

`crabbox usage` reports lease cost and usage estimates from the broker, broken down by user, organization, or the whole fleet.

`crabbox verify` checks a signed run receipt produced by `crabbox run --attest`.

`crabbox vnc` prints (or opens) the connection details for a desktop-capable

`crabbox warmup` leases a box and waits until it is ready: it provisions (or

`crabbox watch` runs a command on a warm lease, then watches the local

Linux portal viewers default to **Match window**: only the connected controller

`crabbox whoami` calls the broker's `/v1/whoami` endpoint and prints the

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.

{{SKILL_ENTRY:decision-lifecycle}}

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.

Your efficient agentic AI coding CLI assistant

AI coding with Aegis governance built into execution: baseline-aware changes, evidence-backed delivery. Free desktop client, your choice of model. 将哲科思维融入 AI 开发…

Android in docker solution with noVNC supported, video recording, mcp server and AI-agent

Your AI assistant, built for the agentic era. Open source and local: talk to it, and it runs your agents, your coding CLIs, your browser and your apps. Windows,…

Verifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.

Let Claude Code and other coding agents drive and debug Chrome from the shell. DOM, network, console and raw CDP as short commands, no screenshots and no MCP ne…

Unofficial, agent-friendly Mercadona shopping CLI (Go) — search products, read prices, build a cart and prepare checkout from the terminal. BYO credentials.

Local-first AI canvas for visual workflows, AI short drama, image/video generation, storyboarding and asset management. ComfyUI, AI agents, MCP & Blender. 本地优先…

Let any AI coding tool — Claude Code, Cursor, Codex — drive your real Chrome. One-prompt setup, muscle memory, local-first.

runs anywhere. uses anything

Open-source dots for the web: an AI agent with its own browser, one that does not get blocked.

Free MIT AI coding agent — no API key needed. Built-in free model, or bring Claude, GPT, Gemini, DeepSeek, Ollama +50 more. Swarm mode, 40+ tools, browser & des…

Open-source AI customer support system. AI-first support, human-ready operations.

A durable, multiplayer, mobile-first web app for Pi agents, built on Pi Durable

Embedded Cypher knowledge graph for Python and Rust. Bundled MCP server, describe() schema, and code-graph parser for LLM agents.

Turn PDFs, books and papers into interactive learning webpages｜将复杂材料转化为可追溯、可测验、可做笔记的学习网页

PhysicsOS 是一个面向初高中物理学习的公益可视化智能体，通过 AI 理解题目并结合物理引擎，将抽象物理过程转化为可交互、可观察、可计算、可验证的真实物理场景。