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/felipesauer/mnemaWrote 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/felipesauer/mnema/plugin)<a href="https://agentmods.dev/plugins/felipesauer/mnema/plugin"><img src="https://agentmods.dev/badge/plugins/felipesauer/mnema/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/felipesauer/mnema/plugin"><img src="https://agentmods.dev/badge/plugins/felipesauer/mnema/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mnema 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 2d 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "mnema",
"version": "0.2.0-beta",
"description": "Puts the project's committed mnema record into the session's opening context without the agent asking, with the notes recorded for it on this machine beside it, the ones near the work first, and connects the mnema MCP server so it can record its own work.",
"author": {
"name": "Felipe Sauer",
"url": "https://github.com/felipesauer"
},
"homepage": "https://github.com/felipesauer/mnema",
"repository": "https://github.com/felipesauer/mnema",
"license": "Apache-2.0",
"keywords": ["audit-trail", "append-only", "accountability", "adr", "local-first"],
"userConfig": {
"mnema_path": {
"type": "string",
"title": "Path to the mnema executable",
"description": "Absolute path of the mnema binary the plugin runs. Leave it as mnema to run the first one on your PATH.",
"default": "mnema"
},
"agent_key": {
"type": "string",
"title": "Agent key",
"description": "The name of an agent key made with `mnema key request --agent <name>` and enrolled with `mnema key enroll --agent`, for the server to sign with. Leave it empty to sign with your own key. This file is read by Claude Code, VS Code and Cursor alike, so no name is filled in for you.",
"default": ""
}
},
"mcpServers": {
"mnema": {
"command": "node",
"args": ["${CLAUDE_PLUGIN_ROOT}/server/launch.mjs", "mcp"],
"env": {
"MNEMA_PLUGIN_BINARY": "${user_config.mnema_path}",
"MNEMA_AGENT_KEY": "${user_config.agent_key}"
}
}
}
}
What it installs
The manifest is a name and a version. 3 skills, 2 hooks travel with it, and installing the plugin installs all of them — 119 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.
- 2d ago Changed · +7 lines 4eceaa795c31
- 4d ago Changed a44b56a8b7e4
- 10d ago Changed · +12 lines 905fdc6ae7e5
- 11d ago Changed 67050f0ce1e7
- 13d ago Changed 237e3548bc9b
- 15d ago Changed 9740cd9b9c67
- 22d ago Changed 8dae1e145266
- 23d ago Changed da64b9597f82
- 1mo ago Changed 8ac94010987a
- 1mo ago First seen · 20 lines scan A 0f6e9fa696cf
mnema is a plugin published in the GitHub repository felipesauer/mnema (4 stars, last pushed yesterday), 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
agent-orchestration
Multi-agent system optimization, agent improvement workflows, and context management.
ownmem
Git-native project memory for AI coding agents, with deterministic local recall, evidence gates, and layered delivery that quotes, points, or abstains.
ijfw
IJFW -- AI efficiency layer for Gemini CLI. 19 workflow skills, 11-event hooks, persistent project memory via MCP. Native policy engine + checkpointing integration. One install layer across 15 AI coding platforms.
project-brain
Folder structure + collaboration protocol so AI sessions can resume project context after compaction or window switch. One brain/ folder, 5 core files (PROJECT/MAP/STATUS/DECISIONS/HANDOFF), and a topic taxonomy.
personal
Personal knowledge and finance automation — autonomous Obsidian vault management (PARA + LLM Wiki) and end-to-end corporate/personal tax preparation from Xero, bank statements, and Google Drive.
imprint
Your habits, imprinted on AI. One extension replaces eleven skills: memory, compression, onboarding, code review, debugging, planning, progress tracking, testing, git workflow, SEO, and copywriting.