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/primeline-ai/kairnWrote 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/primeline-ai/kairn/plugin)<a href="https://agentmods.dev/plugins/primeline-ai/kairn/plugin"><img src="https://agentmods.dev/badge/plugins/primeline-ai/kairn/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.
<a href="https://agentmods.dev/plugins/primeline-ai/kairn/plugin"><img src="https://agentmods.dev/badge/plugins/primeline-ai/kairn/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
kairn 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 4d 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": "kairn",
"version": "0.3.1",
"description": "A local knowledge graph with full-text recall, started by the client over stdio, with no LLM call needed to save or recall.",
"author": {"name": "PrimeLine"},
"license": "MIT",
"icon": "./.claude-plugin/icon.png",
"homepage": "https://primeline.cc/system/kairn",
"repository": "https://github.com/primeline-ai/kairn",
"documentationUrl": "https://github.com/primeline-ai/kairn/blob/main/plugin/README.md",
"supportUrl": "https://github.com/primeline-ai/kairn/issues",
"privacyPolicyUrl": "https://github.com/primeline-ai/kairn/blob/main/plugin/PRIVACY.md",
"keywords": ["memory", "knowledge-graph", "full-text-search", "mcp"]
}
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 — 32 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 15 lines scan A 394e0b8dcd8d
kairn is a plugin published in the GitHub repository primeline-ai/kairn (13 stars, last pushed 4d 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 2026-10-12.
Other plugins, from other repositories
knowledge-graph
Knowledge-graph memory for Claude Code and Codex CLI. Extract and remember patterns, insights and relationships worth preserving across sessions; knowledge is a graph, so nodes gain meaning through edges. Recall at session start, per prompt and per file, self-maintenance, visual editor.
remnic
Universal memory for AI agents — automatic recall, observation, and cross-agent knowledge sharing.
brainlayer
BrainLayer plugin for Claude Code. Uses BrainBar MCP for recall, queued observations, and session-stop sleep.
keymem
Associative long-term memory — recall by key-graph association, plus passive memory surfacing on every prompt.
context-canopy
Portable personal AI context: search and capture knowledge, then read allowlisted user authority across agents.
dt
DomainTome — living knowledge graph for software projects. Bundles the MCP server, auto-invoked read/write skills, and /dt: slash commands for explicit graph operations.