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/joshuaswarren/remnicWrote 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/joshuaswarren/remnic/plugin-claude-code)<a href="https://agentmods.dev/plugins/joshuaswarren/remnic/plugin-claude-code"><img src="https://agentmods.dev/badge/plugins/joshuaswarren/remnic/plugin-claude-code/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/joshuaswarren/remnic/plugin-claude-code"><img src="https://agentmods.dev/badge/plugins/joshuaswarren/remnic/plugin-claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
remnic 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": "remnic",
"description": "Universal memory for AI agents — automatic recall, observation, and cross-agent knowledge sharing",
"version": "10.0.3",
"author": {
"name": "Joshua Warren"
},
"homepage": "https://github.com/joshuaswarren/remnic",
"repository": "https://github.com/joshuaswarren/remnic",
"userConfig": {
"remnic_daemon_token": {
"type": "string",
"title": "Remnic Daemon Bearer Token",
"description": "Bearer token the MCP server sends on every request. Mint via `remnic token generate claude-code` (or `remnic connectors install claude-code` on first install).",
"sensitive": true
},
"remnic_daemon_url": {
"type": "string",
"title": "Remnic Daemon MCP URL",
"description": "Full URL of the Remnic daemon's MCP endpoint. Default http://localhost:4318/mcp. Use http:// loopback or https:// — plaintext http to non-loopback is rejected because the bearer token travels with every request.",
"default": "http://localhost:4318/mcp"
}
},
"mcpServers": {
"remnic": {
"type": "stdio",
"command": "node",
"args": [
"${CLAUDE_PLUGIN_ROOT}/mcp-server-stdio/server.js"
],
"env": {
"REMNIC_PLUGIN_DAEMON_URL": "${user_config.remnic_daemon_url}",
"REMNIC_PLUGIN_DAEMON_TOKEN": "${user_config.remnic_daemon_token}"
}
}
}
}
What it installs
The manifest is a name and a version. 6 skills, 1 agent, 3 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 256 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill remnic-memory-workflow A 54 tokens
- Skill remnic-remember A 39 tokens
- Skill remnic-entities A 41 tokens
- Skill remnic-recall A 35 tokens
- Skill remnic-search A 33 tokens
- Skill remnic-status A 37 tokens
- Agent engram:memory-review A 17 tokens
- Hook PostToolUse A not measured
- Hook SessionStart A not measured
- Hook UserPromptSubmit A not measured
- MCP server remnic A not measured
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 fea82f5444c9
- 3d ago Changed a6f2a07f36a4
- 4d ago Changed e7fcd5b8117a
- 5d ago Changed 136e04b45741
- 9d ago Changed 03ef10773ef6
- 13d ago Changed cc348593d05c
- 14d ago Changed 541f6c8d2552
- 17d ago Changed 3b0da1d1fdea
- 18d ago Changed b4513744c689
- 19d ago First seen · 38 lines scan A bacaf3d7a74d
remnic is a plugin published in the GitHub repository joshuaswarren/remnic (223 stars, last pushed today), 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
plur
Persistent, local-first shared memory for AI agents. Corrections, preferences, and conventions persist across sessions, tools, and machines — stored as plain YAML on your disk, with zero-cost local search.
brainlayer
BrainLayer plugin for Claude Code. Uses BrainBar MCP for recall, queued observations, and session-stop sleep.
alice-memory
Local-first memory for Claude Code: an MCP server and a SessionStart brief on one SQLite file.
alicememory marketplace
Alice Memory plugins for Claude Code.
keymem
Associative long-term memory — recall by key-graph association, plus passive memory surfacing on every prompt.
iai-memory
Persistent local memory for your assistant: every turn captured verbatim, relevant memory injected at session start and before each turn, and fourteen memory tools over MCP. Requires the iai-pme package (pip install iai-pme).