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.
/plugin marketplace add sdsrss/claude-mem-litenpx agentmods add plugins/sdsrss/claude-mem-lite/claude-mem-litegit clone --depth 1 https://github.com/sdsrss/claude-mem-liteWrote 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/sdsrss/claude-mem-lite/claude-mem-lite)<a href="https://agentmods.dev/plugins/sdsrss/claude-mem-lite/claude-mem-lite"><img src="https://agentmods.dev/badge/plugins/sdsrss/claude-mem-lite/claude-mem-lite.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
claude-mem-lite 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 today.
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": "claude-mem-lite",
"version": "3.95.0",
"description": "Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. A lighter, lower-cost alternative to claude-mem (episode batching + a smaller model; cost savings are an internal estimate, not a measured benchmark).",
"author": {
"name": "sdsrss"
},
"repository": "https://github.com/sdsrss/claude-mem-lite",
"license": "MIT",
"keywords": [
"memory",
"context",
"persistence",
"hooks",
"mcp",
"sqlite",
"fts5"
]
}
What it installs
The manifest is a name and a version. 8 commands, 7 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 390 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Command adopt A 101 tokens
- Command bug A 54 tokens
- Command lesson A 62 tokens
- Command tools A 25 tokens
- Command mem A 16 tokens
- Command unadopt A 86 tokens
- Command memory A 25 tokens
- Command update A 21 tokens
- Hook PreToolUse A not measured
- Hook PostToolUse A not measured
- Hook UserPromptSubmit A not measured
- Hook PostToolUseFailure A not measured
- Hook PreCompact A not measured
- Hook Stop A not measured
- Hook SessionStart A not measured
- MCP server mem-lite A not measured
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.
- today Changed 8e9f410239c4
- yesterday Changed 7129473874ed
- 6d ago First seen · 20 lines scan A 273cc4d8bdd0
claude-mem-lite is a plugin published in the GitHub repository sdsrss/claude-mem-lite (57 stars, last pushed yesterday), 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 2026-08-30.
Other plugins, from other repositories
markdown-vault-mcp
Generic markdown vault MCP with hybrid search.
session-tools
Session productivity — cost/token monitoring (ccboard), voice refinement, context catchup, MCP integration templates, and 11 session hooks.
subrosa
Persistent, private memory for Claude Code — every session archived into a local, searchable SQLite database. What's said under the rose stays under the rose.
presence
Continuous-collaboration layer for Claude Code: living project model, outcome telemetry, event digest, and calibrated confidence. Fully local, install-once, applies to every project.
context-compress
Compress tool responses and keep explicitly indexed output searchable without flooding the agent context window.
ai-iq
Memory → Evaluation → Credential → Access Control for AI agents. Persistent memory with W3C Verifiable Credentials, capability-based access control, drift detection, and FSRS-6 spaced repetition.