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/SAIHM-Admin/saihm-mcp-server-proWrote 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/saihm-admin/saihm-mcp-server-pro/gemini-extension)<a href="https://agentmods.dev/plugins/saihm-admin/saihm-mcp-server-pro/gemini-extension"><img src="https://agentmods.dev/badge/plugins/saihm-admin/saihm-mcp-server-pro/gemini-extension/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/saihm-admin/saihm-mcp-server-pro/gemini-extension"><img src="https://agentmods.dev/badge/plugins/saihm-admin/saihm-mcp-server-pro/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
saihm 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": "saihm",
"version": "0.14.1",
"description": "Free-to-start portable memory for AI agents: encrypted, shareable, provably erased.",
"mcpServers": {
"saihm": {
"command": "npx",
"args": ["-y", "@saihm/mcp-server-pro"],
"env": {
"SAIHM_ENDPOINT_URL": "https://saihm.net/mcp"
}
}
}
}
What ships with it
2 files beside gemini-extension.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 fbf440987d12
- 4d ago Changed ed161661af48
- 10d ago Changed 05fb01dfb777
- 11d ago First seen · 15 lines scan A 4a2509dc5bb9
saihm is a plugin published in the GitHub repository SAIHM-Admin/saihm-mcp-server-pro (1 stars, last pushed 2d 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 2026-10-04.
Other plugins, from other repositories
inspeximus
Self-correcting memory for Claude Code. Facts you correct stay corrected, deletions leave a signed receipt you can verify offline, and storing something never calls a model. Also ships the checks: erasureresidue asks whether the bytes actually went — on any store, not just this one.
lians
Financial-grade agent memory for Claude Code — bitemporal recall, SEC 17a-4 audit chain, GDPR/HIPAA crypto-shred, and information barriers. Built for finance, healthcare, and legal teams.
deja
deja-vu memory for Gemini CLI: the coding sessions already on your disk — Gemini CLI, Claude Code, Codex, Cursor and thirty-eight more — searchable and recalled, including work from before it was installed.
ownmem
Git-native project memory for AI coding agents, with deterministic local recall, evidence gates, and layered delivery that quotes, points, or abstains.
knowl
Persistent memory for Claude Code. Facts are typed, sourced, and retired when they change, so a query returns the current answer rather than every answer it has ever held. Local SQLite in your repository — no API key, nothing uploaded.
causal-memory
Persistent causal memory for Claude Code — decisions, outcomes, and lessons that survive compaction. Same-context counterfactuals (natural experiments), a falsifiable prediction ledger, and an activation skill that teaches when to recall and record.