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/L3DigitalNet/Claude-Code-PluginsWrote 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/l3digitalnet/claude-code-plugins/up-docs)<a href="https://agentmods.dev/plugins/l3digitalnet/claude-code-plugins/up-docs"><img src="https://agentmods.dev/badge/plugins/l3digitalnet/claude-code-plugins/up-docs/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/l3digitalnet/claude-code-plugins/up-docs"><img src="https://agentmods.dev/badge/plugins/l3digitalnet/claude-code-plugins/up-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
up-docs 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 1mo 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": "up-docs",
"version": "0.13.1",
"description": "Update documentation across three layers (repo, llm-wiki, Notion) via sub-agent propagation plus drift audit, all on Sonnet. Five commands for targeted updates and comprehensive drift analysis with four-phase convergence.",
"author": { "name": "L3DigitalNet", "url": "https://github.com/L3DigitalNet" },
"homepage": "https://github.com/L3DigitalNet/Claude-Code-Plugins/tree/main/plugins/up-docs"
}
What it installs
The manifest is a name and a version. 5 skills, 4 agents travel with it, and installing the plugin installs all of them — 525 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 1mo ago First seen · 8 lines scan A 6ad5e99d0e02
up-docs is a plugin published in the GitHub repository L3DigitalNet/Claude-Code-Plugins (8 stars, last pushed 1mo 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 2026-09-04.
Other plugins, from other repositories
pm-kit
AI-augmented knowledge vault for Technical PMs and Engineering Leads — PRDs, sprints, decisions, blockers, daily standups, HTML previews, executive briefs.
developer-kit-project-management
Project management and workflow commands.
construction
Skills that give Claude Code the working knowledge of a Project Engineer: split drawing sets and spec manuals, extract schedules, generate submittal logs, tabulate and evaluate bids, draft RFIs and subcontracts, and research building codes.
requirements
Project requirements registry via Google Spreadsheet with GitHub issues sync.
feishu-user-plugin
All-in-one Feishu MCP server + CLI tool for Claude Code — send messages as yourself, read chats (auto-expanded mergeforward), manage docs / bitable / wiki (full CRUD) / drive / OKR (with progress writes) / calendar (read+write) / Tasks v2 / multi-profile auto-switch / real-time WS events. 85 tools + 9 prompts, 3 auth.
okf
Create, follow, and continuously maintain an Open Knowledge Format (OKF) knowledge catalog in every project — a vendor-neutral, plain-markdown standard. Bundles the okf-catalog skill, the okf-auditor agent, and a SessionStart hook that flags any project missing a catalog.