awsh

Plugin awsh from marketplace awsh in Aitherium/awdk. Commands read from the repo's manifest — today.

Skills (115)

• acp-drive

  Drive any external ACP agent from your agent. The Agent Client Protocol lets one agent drive another. When your task needs a different model, a different tool surface, or a sandbox your loop doesn't have, you can hand a sub-problem to an external ACP agent — Claude Code (claude-agent-acp), Codex (co

• acp-serve

  Expose an AitherOS agent to ACP editors. ACP editors — JetBrains IDEs, Zed, VS Code, neovim, Obsidian — drive coding agents over the Agent Client Protocol. adk acp serve makes any AitherOS agent one of those agents: the editor spawns it as a subprocess, and every prompt, permission request and tool

• adk-deepseek-coder

  Fill-in-the-middle, repo packing, and a reward that can fail. DeepSeek-Coder is two useful things at once, and most people only take the first.

• adk-harnesses

  One shell that drives every coding shell. Your agent can hand a task to another coding agent's real product — Claude Code, Codex, Gemini CLI, Aider, OpenCode — and read back one answer.

• adk-unsloth

  Local training and serving, wired to your agent. [Unsloth](https://github.com/unslothai/unsloth) trains LoRA/QLoRA 2x faster with ~70% less VRAM and serves GGUF locally. Pairing it with the ADK gives you a loop that runs entirely on your own hardware: your agent serves from a local model, you fine-t

• adversarial-verification

  Stop grading your own homework. There is one failure that costs more agent-hours than any bug: the agent reads its own diff, decides it is correct, and reports success. Every expensive incident has that shape. A green healthcheck. An HTTP 200. A passing import. A test that goes green. All true, all

• agent-disk-hygiene

  Your coding agents are quietly eating your disk. Nobody tells you this when you start running agents at scale: they generate enormous amounts of disk garbage, in places you will never think to look. Not model weights — *debris*. Throwaway git worktrees, build tarballs, ISO output, caches inside cach

• agent-integrations

  Integrate awdk and AitherOS with mainstream coding agent harnesses (Claude Code, Cursor, Aider, Cline, Codex, Hermes, Roo Code) — both as a CLIENT of cloud providers (OpenRouter, DeepSeek, Anthropic, Moonshot) and as a BACKEND that other agents can use. Two-way integration.

• agent-operating-doctrine

  The standing instructions, tool order and hook wiring one team runs its coding agents under -- no false blockers, a 150-word report cap, search-then-graph, awgit in a shared worktree, and the PreToolUse/Stop gates that make each rule real. Rendered from the team's own AGENTS.md and settings.json by

• agents-everywhere

  Turn an agent idea into a verified, shareable Aitherium tool across awdk, awsh, MCP, WebMCP, PWA, Codex, Claude Code, and other agent CLIs. Use when bootstrapping local inference, connecting existing agents, or packaging a reusable agent tool.

• aither-agent-notebook

  Turn 'build X' into a reviewable, re-runnable plan. A one-shot agent dispatch is a black box: it runs, it either worked or it didn't, and you can't see *why*, replay it with one input changed, or hand it to a human before it touches anything. An Agent Notebook (.anb) fixes that. It's AitherOS's exec

• aither-code-intelligence

  Stand up agent code-search, and prove it actually works. Three layers make an agent stop reading files it doesn't need: [prospector](aither-prospector.md) (*where* to look), [codegraph](aither-codegraph.md) (*which symbols*, and who calls them), [headroom](aither-headroom.md) (*shrink what's left*).

• aither-codegraph

  A call-graph-aware code index your agents can query. Grep finds strings; CodeGraph finds *structure*. It parses a codebase into chunks (functions, classes, routes) with a real call graph — who calls what, who's affected by a change — and lets an agent ask 'where is auth enforced?' and get the symbol

• aither-discord-agent

  Deploy your awdk agent as a Discord bot (automated onboarding). Your awdk agent already has an identity, tools, memory, and inference on your own machine. This skill turns it into a Discord bot with one automated onboarding command — adk onboard --discord — which installs your agent pack, validates

• aither-headroom

  Cut agent token cost with reversible context compression. Agents burn most of their tokens re-sending bulky context every turn: verbose JSON tool output, retrieved documents, file dumps. [headroom](https://github.com/headroomlabs-ai/headroom) (headroom-ai) crushes that content with a SmartCrusher pi

• aither-powered-coding

  Set up any coding agent (Claude Code, Cursor, Aider, Cline) to use AitherOS as its brain — with automatic model switching, 1272 MCP tools, managed agent dispatch, and transparent failover between DeepSeek/Kimi/local models/Anthropic. Supplements awknowledge with the AitherOS-specific infrastructure.

• aither-prospector

  A semantic file-explorer that tells agents WHERE to look. Before an agent greps a 4,000-directory monorepo, it should know the three dirs worth grepping. Prospector (Phase 1, the 'landmark map') clusters a codebase into semantic regions — auth, api, data, ui, service — and answers *'where is rate li

• aither-retrieval

  Aither Retrieval — one surface, every modality. The AitherOS retrieval surface answers one question and returns fused, ranked results from every modality you have — vector similarity, PostgreSQL full-text (tsvector), fuzzy (trigram), graph traversal, code-graph lookup and scoped memory recall. One b

• aither-start

  Zero-to-working-agent on your own machine, for someone who has never written code. Detects the hardware, installs the agent toolkit, downloads a model that actually fits, wires it into whatever agent you already use, and proves it works with a real round-trip. The front door to every other skill in

• aitherbrowser

  Give an agent its own browser on your machine: enable AitherBrowser as an addon, confirm it is serving, then drive a real Chromium with the pilot_* tools — open a page with a goal, read what it renders, click and type, extract structure, keep a login, and close out with a recipe. Use when an agent m

• aitherconnect

  Awconnect — wire your machine, agent, and browser into AitherOS. Awconnect is the onboarding layer: it connects a box you own to AitherOS — detecting local LLMs, setting up the gateway, joining the desktop/agent mesh, and (optionally) linking your browser — so a node you stood up locally becomes rea

• aithermesh

  Stand up a private mesh and onboard nodes + agents to it. AitherMesh is a private overlay network (WireGuard, 10.77.0.0/16) that lets machines you own — anywhere, behind any NAT or firewall — reach each other as if they were on one LAN, and lets your agents run *across* them. This skill uses [Aither

• aithernode

  Awnode — turn a machine's hardware into something your agents can use. awnode is the body of AitherOS. It's a local [MCP](https://modelcontextprotocol.io) server that exposes a machine's real capabilities — GPU/CPU stats, local LLM inference (Ollama / LM Studio), image generation (ComfyUI: Flux, SDX

• aitherzero

  Provision any machine from one config file and a library of numbered PowerShell automation-scripts. Clone the public AitherZero repo, build the module, and run scripts or playbooks on Windows, Linux, or macOS under PowerShell 7. Covers the layered config model, the real command surface, and which pi

• awbrain

  Turn a folder of notes/sessions into a linked-markdown wiki with claims pinned to evidence; ask, verify a claim, trace a figure. Use for grounded recall over your own history.

• awbrowse

  Render a web page through a browser service and print its text or save a screenshot. Use when curl gets a JS shell instead of content, or you need a page image.

• awconnect

  Wire your machine, agent, and browser into AitherOS. Awconnect is the onboarding layer: it connects a box you own to AitherOS — detecting local LLMs, setting up the gateway, joining the desktop/agent mesh, and (optionally) linking your browser — so a node you stood up locally becomes reachable and u

• awdelphi

  Run an anonymous multi-round expert panel (Delphi method) to a converged answer with a trace. Use for a contested design decision or an adversarial multi-reviewer review.

• awdesk

  Put the agent on someone's desk: install the Aither desktop companion from its release assets, keep it talking to a daemon, and use decision cards as the place a question actually reaches a person instead of scrolling past in a transcript. Use when an agent needs a human answer at the right moment,

• awdk

  Run your own AI agent, on your machine, in three commands. [awdk](https://github.com/Aitherium/awdk) is the agent toolkit: an agent runtime, a local shell, inference setup, and control-plane enrollment in one package. You run the model, the agent loop, the memory, and your data on your own box — Ait

• awembed

  Distil an embedding model on your own corpus and prove it beats the teacher on a held-out split; score any served embedders on your data. Use before picking an embedder.

• awflow

  awflow: the deterministic, journaled multi-agent workflow runtime (a library). Use when writing a workflow script that needs replay, resume and a hard token budget.

• awgit-claude-code

  The awgit workflow for Claude Code / an Aither adk agent — how to work when every commit is captured as a semantic edit-op: what to check after a commit, how to read the attribution ledger, how to teleport deltas to a peer node, and how to find/merge node-level conflicts.

• awgit-setup

  Set up awgit (Aither World-Graph git) on a machine — the semantic version-control layer that turns every git commit into a function-level edit-op with a verified GitHub identity, a durable attribution record, and differential sync. Install, init, install the capture hooks, verify.

• awkno

  The man page for the Aither World: look up any aw* brick, law or guide offline. Use on 'what does awX do', 'which brick handles Y', or before building a new aw* tool.

• awknowledge

  Install a measured operating doctrine for running an agentic coding tool at program scale — prompt shape, live-proof gates, plan documents, persistent memory, delegation, compaction and model routing. Mined from 27,939 prompts over 210 days plus a 34-day re-measurement, not invented.

• awmine

  Mine Claude Code, Codex and Pi transcripts for outcomes, lessons, procedures and cost, and pool a team's results. Use to harvest what past sessions learned, compare harnesses, export training/skill candidates, or audit redaction.

• awpredict

  List usable world-model engines and check a class satisfies the WorldModel/EnvironmentAdapter protocol. Use before wiring a new engine or adapter into awpredict.

• awreason

  Ask the awreason reasoning service a question at a chosen depth. Use for a deliberate multi-step answer from the service, or to check it is up.

• awrecurse

  Ask a question of a file larger than the model's context window via recursive chunked querying. Use when a log, dump or document is too big to read whole.

• awrepl

  A persistent Python REPL an agent can keep poking at across calls. Use to inspect live objects instead of re-running a script and guessing from memory.

• awresearch

  Ask a research question and get a cited report whose claims were checked against fetched sources. Use for external research where you need citations, not a plausible essay.

• awrise

  Schedule wakes (jobs) that record why they did or did not fire. Use to add a recurring job, see why one never ran, or check every job's last verdict.

• awscreen

  Find a clickable UI element in a screenshot by plain-language description. Use for vision-based GUI automation when there is no DOM or accessibility tree.

• awshare

  Publish a directory as a verifiable bundle and fetch it back byte-checked; keep many backups while paying for unchanged bytes once (dedupe, incremental snapshots). Use to hand a folder over with integrity proof, or when backups or copies fill a disk.

• awtoll

  Measure what each tool call costs in context from your transcripts. Use on 'what is eating my context', before choosing between two commands, or to gate waste ratcheting down.

• awtunnel

  Validate cloudflared ingress rules and give one local port a public URL. Use before editing tunnel routes, or to expose a local service briefly for a demo or test.

• awvision

  Ask a vision model about an image, the screen or a camera frame; compare two images; watch a source for changes. Use when you need to see pixels, not read text.

• awvoice

  Speech to text and text to speech against a service you host; make the desk avatar speak. Use to transcribe audio, synthesize a reply, or say something aloud.

• awwall

  Fail-closed egress allowlist: declare hosts a workload may reach, check/explain a host, emit hosts/iptables/json. Use when sandboxing an agent's network access.

• bonsai-27b

  Run a 27B model in ~3.8 GB on a plain CPU box. [Bonsai-27B](https://huggingface.co/prism-ml/Bonsai-27B-gguf) (by PrismML) is a 27-billion- parameter model quantized to 1 bit per weight (Q1_0, ~1.1 bit/weight) — the whole thing is a 3.8 GB GGUF that runs on an ordinary CPU with 8 GB of RAM. No GPU, n

• bonsai2-27b

  Serve PrismML's Bonsai 2 27B (Ternary-Bonsai-2-27B, PTQ1_0 5.9 GB or PQ2_0 7.2 GB) as an OpenAI-compatible endpoint with the PrismML llama.cpp fork. Use on 'run Bonsai 2 locally', 'self-host a 27B on a GPU or CPU box', 'why does Bonsai 2 output gibberish'. Stock llama.cpp cannot serve it.

• character-forge

  Character Forge — consistent characters, animation, talking avatars. The definitive procedure for making a character that stays the same character. Every trap below was paid for in real GPU hours and real off-model garbage. Read the Core Law first; it is the whole skill.

• claude-code-hooks-fast

  Make Claude Code hooks cheap, especially on Windows, where every shell-form hook quietly starts four processes on every tool call. Covers exec-form hooks, measuring a hook's real process count, the PowerShell Start-Job trap, fail-soft without `|| true`, and pasting or auto-announcing screenshots.

• claude-model-switcher

  Switch Claude Code between DeepSeek (native 1M context), Kimi, local AitherOS models, and stock Anthropic — one command, no manual config. Use when you hit Claude rate limits, want cheaper/faster models, or need to keep coding on alternative backends.

• compare-versions

  Compare two versions of a file, commit, or release and report structural and behavioral diffs

• concurrent-safe-git

  Commit safely in a worktree you do NOT have to yourself — several agents, a teammate, and a maintenance loop all editing and committing at once. The pathspec commit form, the four commands that silently destroy someone else's work, and the stat-dirty refresh that unblocks a merge git only THINKS is

• debt-ledger

  Keep one master tech-debt ledger that actually gets written to — severity tables, collision-free ids via the bundled next_debt_id.py, and the discipline that debt found is debt recorded in the same turn. Includes the stop-hook that blocks finishing a code change without a debt check.

• decision-cards

  Decision Cards — structured asks that actually reach the owner. Decision cards surface a decision, blocker, or critical fact as a window the owner can click, type into, and answer — without burying it in terminal prose that stays unread.

• deer-flow

  Run ByteDance's DeerFlow — a LangGraph-based super-agent harness for autonomous research, coding and content creation with sub-agents, persistent memory and sandboxed execution. Covers Docker and local setup, pointing it at your own OpenAI-compatible endpoint via config.yaml, its MCP server support

• dependencies

  Manage project dependencies, check for updates, and scan for vulnerabilities

• dgx-spark-deepseek-v4

  A 284B model at ~30 tok/s on one desk machine. Serve DeepSeek-V4-Flash-0731 — 284B parameters, 13B active, MoE — on a single NVIDIA DGX Spark (GB10, 121 GB unified memory, ARM64), with the vendor's own speculative-decoding drafter attached, and verify it is really working.

• do-my-taxes

  Do My Taxes — personal tax preparation workflow. Personal 1040 tax preparation using document ingestion, transaction categorization, deduction discovery, and CPA-ready output.

• docker-network-ops

  Diagnose container DNS and networking without fooling yourself. Container networking faults are latency-shaped, load-shaped and client-specific. Almost every instinctive way to measure them returns a confident wrong answer. This skill is the set of measurements that survive, plus the tool that runs

• docker-wsl2-build-safety

  Stop bulk builds from killing Docker Desktop (and don't blame the disk). Docker Desktop on Windows runs its engine inside a WSL2 VM with a fixed memory ceiling. Build a lot of images while a lot of containers are resident and the VM's storage layer can collapse — taking every container down with it.

• docker-wsl2-disk-reclaim

  Your drive is full and `docker system df` is lying to you. Docker Desktop on WSL2 stores everything in a dynamically-expanding VHDX that never shrinks. You delete 200GB of images, docker system df drops, and your drive stays exactly as full as before. People then go looking for the space in the wron

• event-loop-debugger

  Detect, pin, and fix asyncio event-loop stalls in Python services — a synchronous call or CPU-bound work blocking the loop — including on the free-threaded python3.14t build where py-spy and gdb fail.

• finetune-that-improves

  Train your own model without making it worse. Most fine-tunes lose to the model they started from, and you cannot tell from the score. This is what we learned doing it wrong seven times in a row.

• floci-local-cloud

  Exercise cloud automation (AWS/Azure/GCP/OCI) against local MIT-licensed emulators instead of real accounts — no credentials, no credit burn, no live instance at risk. Load before writing or testing anything that calls a cloud SDK: rental/provisioning code, S3 artifact sync, IAM or secrets paths, or

• github-actions-image-pipeline

  Run GitHub Actions image pipelines without rebuilding the same images on every push, or paying an hour-long cold build for a typo. The build-once/deploy-many architecture, why GitHub Actions' 10GB cache silently evicts your base image so every build is cold, the disk-reclaim step an ML base needs on

• github-agentic-c2

  Use GitHub as the control plane for autonomous agents — issues as the task queue, PRs as the review gate, git as the conflict-resolution protocol, Actions on self-hosted runners as your own compute, and Projects as the board. Load when wiring agents to run unattended work with an audit trail, when d

• github-artifact-quota

  The storage limit that silently freezes your deploys. Your site stops updating. Not breaking — updating. Every page returns 200, every workflow reports green on the commits you looked at, and the content is days old.

• github-runner-fleet

  Stand up, verify and repair a fleet of self-hosted GitHub Actions runners on one Windows host. Load when CI jobs sit queued while `gh api .../actions/runners` shows an online runner, when adding parallel capacity, when a workflow cannot get a runner, or before deleting any runner registration. Encod

• gpu-vram-attribution

  When the platform cannot tell you who is using the GPU. You have one GPU and a dozen containers on it. Something is starving. You run nvidia-smi to find out who is holding the memory, and it tells you nothing useful. Now what?

• graph-a-repo

  Turn a repository OR a knowledge base into a graph an agent can actually answer from — pick the right embedder, stand it up, ingest, and PROVE both halves work (the vectors are the right dimension AND retrieval returns the ingested content). The operational runbook for the graphrag toolpack; pairs w

• graph-rag-agent

  Build a knowledge graph and an agent that owns it. Point [awdk](awdk.md) at a folder of documents (or a codebase) and it builds a knowledge graph — chunked, embedded, and linked — then give a dedicated agent that graph as its memory so it answers from *your* material instead of guessing. This is gra

• hermes-agent

  Install Nous Research's Hermes agent and run it on your own model — a self-improving agent with persistent memory, autonomous skill creation, cron automation and multi-platform messaging. Covers pointing it at a local OpenAI-compatible endpoint, adding the AitherOS toolset over MCP, and the exact co

• hetzner-fleet

  Provision bare metal and VPS directly into your mesh from Hetzner Cloud. Hetzner Cloud is a European VPS provider with a flat, pleasant API: one bearer token, no IAM, no service accounts. This skill wires it in as a provisioning target so a single deploy call spins up a server, attaches your SSH key

• i-have-adhd

  Shape every answer, report, card and status line for a reader with ADHD: lead with the next action, number the steps, cap what is visible at five, restate state, make wins visible, end with one concrete next step. Use on /i-have-adhd, "adhd mode", or when a reader says the output buries the answer.

• install-skills
• lan-latency
• local-image-generation
• local-inference
• local-research
• moat-guard
• model-fitness-benchmark
• model-quantization
• nvidia-cuda-mcp
• ods
• omninode-node
• openclaw
• performance
• pooled-inference
• prove-it-live
• ps5-bridge
• purecss-art
• ramble-driven-development
• recover-docker
• refactor
• repo-intake
• repo-is-not-a-runtime
• repo-to-website
• resume-all
• safe-bulk-rename
• salescompel
• secretguard
• security-audit
• ship-an-app-free
• split-inference
• tau
• website-as-code
• windows-kernel-leak
• worktrees
• xy-charts
• zeroauthy

Subagents (1)

• aw

  Delegates to a session on the local awsh harness daemon instead of a Claude model. Use when the user asks for another model, provider or coding agent by name ("have gemini review this", "run codex on it", "ask kimi", "get a second opinion from another model"), or for a cheap bulk pass. The harness r

MCP servers (4)

• awrelay

  runs: python -m adk.harnesses.brick_mcp awrelay

• awfind

  runs: python -m adk.harnesses.brick_mcp awfind

• awgraph

  runs: python -m adk.harnesses.brick_mcp awgraph

• awdecide

  runs: python -m adk.harnesses.brick_mcp awdecide

Similar plugins