agentmods.dev

agent-knowledge

agent-knowledge is a plugin for Claude Code from keshrath/agent-knowledge. Its manifest loads nothing; the 1 skill, 1 MCP server it bundles cost 96 tokens per session together, scanned A, original, MIT.

A cross-session memory system for coding agents: a Git-synced Markdown knowledge base with search, a typed knowledge graph, and session distillation.

In plain words
What is it for?
Use it to store and retrieve notes, connect related facts, and review accumulated knowledge in the /knowledge pane.
Why use it?
It lets an agent retain and find project knowledge across separate sessions instead of relying only on the current conversation.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

not rated 19repo 13d ago A scan tokens not measured original MIT

Good fit Use it to store and retrieve notes, connect related facts, and review accumulated knowledge in the /knowledge pane.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add keshrath/agent-knowledge
/plugin install agent-knowledge
View source ↗ keshrath/agent-knowledge npmjs.com
Install

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.

Clone the repo
git clone --depth 1 https://github.com/keshrath/agent-knowledge

Made for: Claude Code.

Wrote 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.

agentmods badge for agent-knowledge

README.md
[![agentmods](https://agentmods.dev/badge/plugins/keshrath/agent-knowledge/plugin/github.svg)](https://agentmods.dev/plugins/keshrath/agent-knowledge/plugin)
Your own site
<a href="https://agentmods.dev/plugins/keshrath/agent-knowledge/plugin"><img src="https://agentmods.dev/badge/plugins/keshrath/agent-knowledge/plugin/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.

agentmods 80×15 button for agent-knowledge

Your own site · 80×15
<a href="https://agentmods.dev/plugins/keshrath/agent-knowledge/plugin"><img src="https://agentmods.dev/badge/plugins/keshrath/agent-knowledge/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill, 1 MCP server cost 96 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

agent-knowledge 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 13d 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.

plugin/.claude-plugin/plugin.json · 15 lines

What it actually says

{
  "name": "agent-knowledge",
  "displayName": "agent-knowledge",
  "version": "2.0.0",
  "description": "Cross-session memory for AI coding agents: a git-synced Markdown knowledge base with hybrid search, a typed knowledge graph and session distillation, browsed in the /knowledge pane.",
  "author": {
    "name": "keshrath"
  },
  "homepage": "https://github.com/keshrath/agent-knowledge",
  "repository": "https://github.com/keshrath/agent-knowledge",
  "license": "MIT",
  "keywords": ["mcp", "memory", "knowledge-graph", "semantic-search", "claude-code"],
  "types": "./types/index.d.ts"
}
Contents

What it installs

The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 96 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

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.

  1. 13d ago First seen · 15 lines scan A db834fbf2f21

Subscribe to this mod's changes

agent-knowledge is a plugin published in the GitHub repository keshrath/agent-knowledge (19 stars, last pushed 13d 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 2026-10-25.

Memory and contextai-agentsembeddingsknowledge-basemcp
Related

agent-knowledge compared with plugins from other repositories

agent-knowledge next to 6 plugins from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agent-knowledgekeshrath/agent-knowledgePlugin1913d agoMITA—Claude Code
markdown-vault-mcppvliesdonk/markdown-vault-mcpPlugin38yesterdayMITA—Claude Code
distillerynorrietaylor/distilleryPlugin25yesterdaynoneA—Claude Code
kb-workflowriemannulus/knowledge-basePlugin12mo agoMITA—Claude Code
mybrainrobertsfeir/mybrainPlugin15mo agoApache-2.0A—Claude Code
obsidian-wikiAr9av/obsidian-wikiPlugin3.7kyesterdayMITA—Claude Code
mindosGeminiLight/MindOSPlugin70414d agoMITA—Claude Code