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/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/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/lttr/claude-marketplace/aiwork"><img src="https://agentmods.dev/badge/plugins/lttr/claude-marketplace/aiwork.svg" alt="Reviewed on agentmods" width="80" 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 14d 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.
What it actually says
{
"name": "aiwork",
"version": "3.15.0",
"description": ".aiwork/ folder protocol for AI work artifacts, plus skills for the full loop: intent → spec → tickets → implement → review",
"author": {
"name": "Lukas Trumm",
"email": "[email protected]"
},
"keywords": [
"aiwork",
"protocol",
"artifacts",
"plans",
"intent",
"specs",
"tickets",
"implement",
"triage",
"code-review",
"review",
"workflow",
"convention"
]
}
What it installs
The manifest is a name and a version. 12 skills, 2 hooks travel with it, and installing the plugin installs all of them — 605 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 134 tokens
- Skill triage A 78 tokens
- Skill code-review-diff A 74 tokens
- Skill grill-with-docs A 58 tokens
- Skill to-tickets A 26 tokens
- Skill prototype A 50 tokens
- Skill to-spec A 30 tokens
- Skill next-steps A 50 tokens
- Skill implement A 19 tokens
- Skill wait-what A 21 tokens
- Skill tdd A 33 tokens
- Hook Stop A not measured
- Hook SubagentStop A not measured
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.
- 14d ago Changed c25a0e51b559
- 18d ago Changed b1722da050a4
- 27d ago Changed d7d20ccc3968
- 1mo ago Changed 89df81dc8929
- 1mo ago Changed e13519d5c9f8
- 1mo ago Changed · +1 lines 2931065ff218
- 1mo ago Changed 7825f396fe82
- 1mo ago First seen · 24 lines scan A a680a70792b4
aiwork is a plugin published in the GitHub repository lttr/claude-marketplace (2 stars, last pushed 14d 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
construction-pm
Create project estimates, change orders, progress reports, and RFI responses for construction project management.
taskwarrior
Token-dense recipes for taskwarrior CLI: dense listings, single-field lookups, batched exports, full-text search.
claude-orchestration
Parallel multi-agent orchestration for complex features with Task-based coordination and git-wt --stack worktree isolation.
cc-code
A plugin that organizes software development into a fixed PM, architect, developer, and QA cycle, with separate files for requirements, design, implementation, and acceptance.
pf-workflow
Spec-driven workflow toolkit for multi-agent CLI development: task packets, journal, retro, autopilot.
weft
Deterministic workflow tracking with event-sourced logs for Claude Code.