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/SummerSec/SumSec-SkillsWrote 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/summersec/sumsec-skills/claude-md-management)<a href="https://agentmods.dev/plugins/summersec/sumsec-skills/claude-md-management"><img src="https://agentmods.dev/badge/plugins/summersec/sumsec-skills/claude-md-management/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/summersec/sumsec-skills/claude-md-management"><img src="https://agentmods.dev/badge/plugins/summersec/sumsec-skills/claude-md-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
claude-md-management 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.
This is a copy
91% identical to claude-md-management — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"name": "claude-md-management",
"description": "Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.",
"version": "1.0.47",
"author": {
"name": "Anthropic",
"email": "[email protected]"
}
}
What it installs
The manifest is a name and a version. 1 skill, 1 command travel with it, and installing the plugin installs all of them — 93 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 Changed 1659977f643b
- 1mo ago Changed 21c3140c6d78
- 1mo ago First seen · 10 lines scan A aaf418d55252
claude-md-management is a plugin published in the GitHub repository SummerSec/SumSec-Skills (8 stars, last pushed 1mo ago), licensed Apache-2.0. 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. It is 91% identical to claude-md-management, differing in 2 lines, and is treated as a copy.
Other plugins, from other repositories
openviking-memory
Long-term semantic memory for Claude Code, powered by OpenViking. Auto-recall relevant memories at session start and capture important information during conversations.
mem9
Persistent cloud memory for Claude Code. Requires Node.js 18+, auto-initializes auth on startup, recalls memories on each user turn, and uploads structured conversation turns to mem9.
lingshu-memory
A plugin that connects a coding agent to a long-term memory service and supplies 16 work rules. It supports memory across conversations and records whether saved information was committed.
causal-memory
Persistent causal memory for Claude Code — decisions, outcomes, and lessons that survive compaction. Same-context counterfactuals (natural experiments), a falsifiable prediction ledger, and an activation skill that teaches when to recall and record.
l123-harness
A project structure for keeping an AI agent’s memory outside the model in three layers: persistent notes, an index, and detailed records. It also provides templates, approval controls, event logs, context-saving procedures, and weekly review tools.
open-knowledge-vault
Create and maintain portable Open Knowledge Format vaults with optional Obsidian and Dataview views.