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.
/plugin marketplace add lttr/claude-marketplacenpx agentmods add plugins/lttr/claude-marketplace/aiworkgit clone --depth 1 https://github.com/lttr/claude-marketplaceWrote 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/lttr/claude-marketplace/aiwork)<a href="https://agentmods.dev/plugins/lttr/claude-marketplace/aiwork"><img src="https://agentmods.dev/badge/plugins/lttr/claude-marketplace/aiwork.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
aiwork 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 today.
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.
What it actually says
{
"name": "aiwork",
"version": "3.9.0",
"description": ".aiwork/ folder protocol for AI work artifacts, plus skills for the full loop: triage → spec → tickets → implement → review",
"author": {
"name": "Lukas Trumm",
"email": "[email protected]"
},
"keywords": [
"aiwork",
"protocol",
"artifacts",
"plans",
"specs",
"tickets",
"implement",
"triage",
"code-review",
"review",
"workflow",
"convention"
]
}
What it installs
The manifest is a name and a version. 11 skills travel with it, and installing the plugin installs all of them — 597 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill implement-spec A 32 tokens
- Skill aiwork-protocol A 128 tokens
- Skill code-review-diff A 74 tokens
- Skill grill-with-docs A 58 tokens
- Skill triage A 78 tokens
- Skill to-tickets A 26 tokens
- Skill to-spec A 30 tokens
- Skill agent-browser A 98 tokens
- Skill implement A 19 tokens
- Skill wait-what A 21 tokens
- Skill tdd A 33 tokens
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.
- today Changed 7825f396fe82
- 5d ago First seen · 24 lines scan A a680a70792b4
aiwork is a plugin published in the GitHub repository lttr/claude-marketplace (2 stars, last pushed 2d ago), licensed MIT. 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 2026-08-31.
Other plugins, from other repositories
section-508
Expert Section 508 compliance advisor for US federal ICT accessibility — VPAT/ACR completion, WCAG 2.0 AA audits, remediation planning, PDF accessibility, procurement language, keyboard and screen reader testing, undue burden assessments, and agency compliance workflows.
kiln
Multi-model software creation pipeline. A conversation becomes running, tested software — an interactive brainstorm, then an autonomous build: GPT-5.6 writes the code, Claude shapes the plans and interfaces, and each family inspects the work of the other.
kit
Spec-driven Claude Code workflow with verification pipeline. Hooks, slash commands, and verification subagents.
tailscale
Tailscale CLI reference and safe patterns for exposing local services over a tailnet.
understanding
Understand a topic or a bug: minimal explanations and root-cause diagnosis.
superpowers-graph
The Superpowers software-development methodology executed as a guarded state machine: 21 typed nodes, 96 total exit guards, 9 bounded retry loops, durable run state that survives compaction, and a ledger recording every step that could not run.