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/RohiRIK/OpenLtmWrote 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/rohirik/openltm/openltm)<a href="https://agentmods.dev/plugins/rohirik/openltm/openltm"><img src="https://agentmods.dev/badge/plugins/rohirik/openltm/openltm/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/rohirik/openltm/openltm"><img src="https://agentmods.dev/badge/plugins/rohirik/openltm/openltm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
openltm 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 yesterday.
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": "openltm",
"description": "OpenLTM — Long-Term Memory for AI coding agents: semantic search, context injection, session learning",
"version": "2.19.0",
"author": {
"name": "RohiRIK"
},
"mcpServers": {
"memory": {
"command": "bun",
"args": [
"run",
"${CLAUDE_PLUGIN_ROOT}/src/mcp-server.ts"
],
"env": {
"LTM_PLUGIN_DATA": "${CLAUDE_PLUGIN_DATA}"
}
}
},
"skills": "./skills/",
"agents": [
"./agents/git-learner.md",
"./agents/ltm-planner.md"
]
}
What it installs
The manifest is a name and a version. 6 skills, 7 commands, 2 agents, 6 hooks travel with it, and installing the plugin installs all of them — 741 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill MemoryReview A 103 tokens
- Skill GitLearn A 71 tokens
- Skill Ltm A 98 tokens
- Skill agent-trust-boundaries A 19 tokens
- Skill command-path-safety A 19 tokens
- Skill secret-safe-handling A 21 tokens
- Command admin A 38 tokens
- Command memory A 41 tokens
- Command analyze-context A 39 tokens
- Command onboard A 31 tokens
- Command health B 37 tokens
- Command project B 31 tokens
- Command server B 52 tokens
- Agent ltm-planner A 81 tokens
- Agent git-learner A 60 tokens
- Hook PostToolUse A not measured
- Hook SessionStart A not measured
- Hook PreCompact A not measured
- Hook UserPromptSubmit A not measured
- Hook SessionEnd A not measured
- Hook Stop 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.
- yesterday Changed 89c9bb9a6a27
- 2d ago Changed 27869114a0bf
- 5d ago Changed b4d57a458215
- 12d ago Changed 677d6394778a
- 19d ago Changed 8794465e7800
- 22d ago Changed 9fc77406472b
- 1mo ago First seen · 26 lines scan A 14c3be5013e3
openltm is a plugin published in the GitHub repository RohiRIK/OpenLtm (28 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
mem0
Cross-session memory and token savings for coding agents.
hippo-memory
Make your agent's memory work like a brain. Hippo is long-term memory for coding agents.
emem
Shared, verifiable memory for AI agents. Two layers, one trust surface. Earth-scale fact substrate: every patch of ground gets a 64-bit address (cell64, about 9.55 m), and every measurement at that cell is a signed fact keyed by (cell, band, tslot), ed25519-signed by the responder over the blake3 of its canonical CBOR.
emem
Verifiable shared memory for AI agents: resolve a place to one canonical address, recall Ed25519-signed Earth-observation facts, and hand another agent a token it can check offline. Reads need no key; the data is maintained by machines (satellites, sensors, open-data connectors), and agents write their own signed…
cc-hud
Compact statusline HUD for Claude Code — context, agents, rate limits.
goodmem
GoodMem memory infrastructure for AI agents. Use Python SDK skills to write code that manages embedders, spaces, and memories, or use MCP tools to perform GoodMem operations directly via natural language.