Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Aitherium/awdkWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/aitherium/awdk/claude_mod)<a href="https://agentmods.dev/plugins/aitherium/awdk/claude_mod"><img src="https://agentmods.dev/badge/plugins/aitherium/awdk/claude_mod/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/aitherium/awdk/claude_mod"><img src="https://agentmods.dev/badge/plugins/aitherium/awdk/claude_mod.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
awsh scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What it installs
The manifest is a name and a version. 104 skills, 1 agent, 4 MCP servers travel with it, and installing the plugin installs all of them — 7,073 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill docker-network-ops A 64 tokens
- Skill github-artifact-quota A 50 tokens
- Skill awgit-claude-code A 70 tokens
- Skill awknowledge A 65 tokens
- Skill local-image-generation A 85 tokens
- Skill ramble-driven-development A 43 tokens
- Skill adk-harnesses A 49 tokens
- Skill adversarial-verification A 83 tokens
- Skill agent-integrations A 74 tokens
- Skill aither-code-intelligence A 113 tokens
- Skill aither-codegraph A 101 tokens
- Skill aither-powered-coding A 104 tokens
- Skill claude-model-switcher A 64 tokens
- Skill decision-cards A 51 tokens
- Skill dgx-spark-deepseek-v4 A 88 tokens
- Skill finetune-that-improves A 51 tokens
- Skill github-agentic-c2 A 101 tokens
- Skill github-runner-fleet A 106 tokens
- Skill gpu-vram-attribution A 58 tokens
- Skill graph-a-repo A 86 tokens
- Skill install-skills A 77 tokens
- Skill model-fitness-benchmark A 91 tokens
- Skill pooled-inference A 91 tokens
- Skill safe-bulk-rename A 111 tokens
- Skill ship-an-app-free A 0 tokens
- Skill adk-deepseek-coder A 42 tokens
- Skill adk-unsloth A 104 tokens
- Skill agent-operating-doctrine A 86 tokens
- Skill aither-agent-notebook A 137 tokens
- Skill aither-discord-agent A 115 tokens
- Skill aither-headroom A 130 tokens
- Skill aither-retrieval A 80 tokens
- Skill aitherzero A 73 tokens
- Skill compare-versions A 22 tokens
- Skill concurrent-safe-git A 98 tokens
- Skill debt-ledger A 62 tokens
- Skill deer-flow A 85 tokens
- Skill dependencies A 14 tokens
- Skill do-my-taxes A 36 tokens
- Skill docker-wsl2-build-safety A 90 tokens
- Skill docker-wsl2-disk-reclaim A 85 tokens
- Skill event-loop-debugger A 51 tokens
- Skill nvidia-cuda-mcp A 85 tokens
- Skill performance A 12 tokens
- Skill prove-it-live A 70 tokens
- Skill refactor A 15 tokens
- Skill repo-is-not-a-runtime A 54 tokens
- Skill resume-all A 33 tokens
- Skill security-audit A 15 tokens
- Skill split-inference A 86 tokens
- Skill website-as-code A 40 tokens
- Skill aither-prospector A 116 tokens
- Skill aithermesh A 132 tokens
- Skill awgit-setup A 64 tokens
- Skill floci-local-cloud A 0 tokens
- Skill omninode-node A 122 tokens
- Skill purecss-art A 120 tokens
- Skill repo-to-website A 42 tokens
- Skill acp-drive A 117 tokens
- Skill aithernode A 121 tokens
- Skill graph-rag-agent A 99 tokens
- Skill moat-guard A 38 tokens
- Skill model-quantization A 44 tokens
- Skill xy-charts A 114 tokens
- Skill acp-serve A 100 tokens
- Skill aitherconnect A 86 tokens
- Skill awconnect A 82 tokens
- Skill recover-docker A 32 tokens
- Skill awshare A 54 tokens
- Skill awrise A 39 tokens
- Skill awvision A 40 tokens
- Skill awvoice A 38 tokens
- Skill awbrain A 41 tokens
- Skill awbrowse A 38 tokens
- Skill awdelphi A 40 tokens
- Skill awembed A 41 tokens
- Skill awflow A 36 tokens
- Skill awkno A 48 tokens
- Skill awmine A 34 tokens
- Skill awpredict A 33 tokens
- Skill awreason A 34 tokens
- Skill awrepl A 35 tokens
- Skill awresearch A 34 tokens
- Skill awtoll A 40 tokens
- Skill awtunnel A 38 tokens
- Skill awwall A 40 tokens
- Skill awrecurse A 38 tokens
- Skill awscreen A 31 tokens
- Skill character-forge B 56 tokens
- Skill repo-intake B 140 tokens
- Skill hetzner-fleet C 79 tokens
- Skill agents-everywhere C 66 tokens
- Skill local-inference C 86 tokens
- Skill agent-disk-hygiene C 70 tokens
- Skill aither-start C 68 tokens
- Skill bonsai2-27b C 109 tokens
- Skill tau C 0 tokens
- Skill hermes-agent C 74 tokens
- Skill ods C 79 tokens
- Skill openclaw C 80 tokens
- Skill awdk C 106 tokens
- Skill bonsai-27b C 139 tokens
- Skill secretguard C 13 tokens
- Skill github-actions-image-pipeline D 111 tokens
- Agent aw B 0 tokens
- MCP server awdecide A not measured
- MCP server awfind A not measured
- MCP server awgraph A not measured
- MCP server awrelay A not measured
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago Changed · +5 lines fb9a06e9cf6a
- 17d ago First seen · 10 lines scan A fa87fc615e9f
awsh is a plugin published in the GitHub repository Aitherium/awdk (11 stars, last pushed yesterday), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-21.
Other plugins, from other repositories
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
superpowers
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques.
knowledge-work-plugins marketplace
Plugin marketplace listing 123 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.