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.
npx agentmods add skills/matrixorigin/memoria/plugin-developmentnpx skills add matrixorigin/memoria --skill plugin-developmentgit clone --depth 1 https://github.com/matrixorigin/memoriaWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00037 | $0.01142 |
| Opus 5 | $0.00018 | $0.00571 |
| Sonnet 5 | $0.00007 | $0.00228 |
| Haiku 4.5 | $0.00004 | $0.00114 |
Grade A, and why
plugin-development 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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quick Start
memoria plugin init --dir ./my-plugin --name my-governance \
--capabilities governance.plan,governance.execute
Creates:
my-plugin/
├── manifest.json # Plugin metadata, permissions, limits
└── policy.rhai # Governance logic (Rhai script)
manifest.json
{
"name": "memoria-my-governance",
"version": "0.1.0",
"api_version": "v1",
"runtime": "rhai",
"entry": { "rhai": { "script": "policy.rhai", "entrypoint": "memoria_plugin" } },
"capabilities": ["governance.plan", "governance.execute"],
"compatibility": { "memoria": ">=0.1.0" },
"permissions": { "network": false, "filesystem": false, "env": [] },
"limits": { "timeout_ms": 500, "max_memory_mb": 32, "max_output_bytes": 8192 },
"integrity": { "sha256": "", "signature": "", "signer": "" },
"metadata": { "display_name": "My Governance Plugin" }
}
Key fields:
runtime:rhai(sandboxed) orgrpc(remote service)capabilities: must includegovernance.planand/orgovernance.executeintegrity: auto-filled bymemoria plugin publish
policy.rhai
fn memoria_plugin(ctx) {
if ctx["phase"] == "plan" {
let review = decision("my-plugin:check", "Description", 0.8);
review["evidence"] = [evidence("source", "What was found")];
return #{
requires_approval: false,
actions: [review],
estimated_impact: #{ "my.metric": 1.0 }
};
}
if ctx["phase"] == "execute" {
return #{ warnings: [], metrics: #{ "my.metric": 1.0 } };
}
return #{};
}
Built-in helpers: decision(id, reason, confidence), evidence(source, description)
Runtime Types
| Runtime | Sandboxing | Use Case |
|---|---|---|
rhai |
In-process, memory/time limited | Simple rules, no external deps |
grpc |
Out-of-process, network call | Complex logic, external services |
Development Workflow
1. Local dev (no signature, no DB)
MEMORIA_GOVERNANCE_ENABLED=true \
MEMORIA_GOVERNANCE_PLUGIN_DIR=./my-plugin \
memoria serve
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 First seen · 136 lines · 37 tokens per session scan A 9d8bba1f7c20
plugin-development is a skill published in the GitHub repository matrixorigin/memoria (591 stars, last pushed 6d ago), licensed Apache-2.0. It adds 37 tokens to every session and 1,142 once invoked, about $0.0002 per session on Opus 5. 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 skills, from other repositories
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
publish-registry
Publish @agentos-software/ registry packages from AgentOS. Use whenever the user asks to publish or release registry software/agent packages.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.
lazarus-group
Adversary-emulation profile for Lazarus Group (G0032, aka Hidden Cobra / Diamond Sleet / Labyrinth Chollima), a North Korean RGB-linked actor conducting espionage, destructive, and financially motivated operations.