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/underpass-ai/kmpWrote 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/underpass-ai/kmp/marketplace)<a href="https://agentmods.dev/plugins/underpass-ai/kmp/marketplace"><img src="https://agentmods.dev/badge/plugins/underpass-ai/kmp/marketplace/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/underpass-ai/kmp/marketplace"><img src="https://agentmods.dev/badge/plugins/underpass-ai/kmp/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
underpass marketplace 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 16d 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": "underpass",
"description": "KMP by Underpass",
"owner": {
"name": "Underpass AI",
"url": "https://underpassai.com"
},
"plugins": [
{
"name": "kmp",
"description": "Local-first agent memory that preserves what happened, when and why, with a shared ChronoLoom view.",
"source": {
"source": "git-subdir",
"url": "https://github.com/underpass-ai/kmp.git",
"path": "plugins/kmp",
"ref": "v0.25.0"
}
}
]
}
The plugins it lists here
This marketplace lists 1 plugin kept in the same repository. Each has its own page, its own measurements and its own install command.
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.
- 16d ago Changed 9e6a11da9fa0
- 23d ago Changed aba0bd5e0d2e
- 24d ago Changed 6f0790931cfe
- 26d ago Changed 0636025626df
- 27d ago Changed 72bbcf4bf16b
- 1mo ago Changed 0cad718f7c57
- 1mo ago Changed d391013658f6
- 1mo ago Changed cd40aa10b867
- 1mo ago Changed e3e20ad59a66
- 1mo ago First seen · 21 lines scan A 61a558d20d22
underpass marketplace is a plugin published in the GitHub repository underpass-ai/kmp (0 stars, last pushed 10d ago), 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
titen-memory
Use Titen's evidence-grounded collaborative memory. The local stdio mode needs no configuration; a served Titen endpoint is the alternative for a shared store.
orgkit
Turn a Claude Code repo into a self-organizing org: per-role memory brains auto-injected at session start, inline lessons auto-promoted, and a live ORG.md. Ships slash commands + lifecycle hooks plus a one-command onboarding flow.
token-optimizer
Context-window optimization tools (caching, compression, smart file tooling) for the Gemini CLI.
openloomi
Connect Claude Code to your local OpenLoomi runtime. One-command install, mirror Claude's lifecycle onto the Loomi Pet, and auto-archive every Stop into your OpenLoomi memory. Talks to your local OpenLoomi over HTTP and the OpenLoomi helper CLI. AI provider config is owned by OpenLoomi itself — this plugin never reads.
Elpis
Provider-neutral terminal agent shell for controlled context, persistent memory, safe execution, and session continuity.
yantrikdb
Cognitive memory for AI agents — semantic recall, a knowledge graph, contradiction detection and procedural learning. Local-first: one SQLite file, no account, no telemetry.