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 skills add matrixorigin/memoria --skill architecturegit clone --depth 1 https://github.com/matrixorigin/memoriaWrote 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/skills/matrixorigin/memoria/architecture)<a href="https://agentmods.dev/skills/matrixorigin/memoria/architecture"><img src="https://agentmods.dev/badge/skills/matrixorigin/memoria/architecture/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/skills/matrixorigin/memoria/architecture"><img src="https://agentmods.dev/badge/skills/matrixorigin/memoria/architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00033 | $0.01908 |
| Opus 5.5 | $0.00013 | $0.00763 |
| Sonnet 5.5 | $0.00007 | $0.00382 |
| Haiku 4.5 | $0.00003 | $0.00191 |
Grade A, and why
architecture 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workspace Layout
memoria/ # Cargo workspace root
├── crates/
│ ├── memoria-core/ # Shared types: MemoriaError, Memory, MemoryType
│ ├── memoria-storage/ # SqlMemoryStore — all SQL queries, migrations
│ ├── memoria-service/ # Business logic
│ │ └── src/
│ │ ├── service.rs # MemoryService — main entry point
│ │ ├── scheduler.rs # GovernanceScheduler — periodic tasks + leader election
│ │ ├── config.rs # Config struct (reads env vars)
│ │ ├── distributed.rs # DistributedLock, AsyncTaskStore traits + SQL impls
│ │ ├── governance/ # GovernanceStrategy trait, DefaultGovernanceStrategy
│ │ └── plugin/ # Plugin system (manifest, repository, rhai, grpc)
│ ├── memoria-api/ # REST API (axum)
│ │ └── src/
│ │ ├── lib.rs # build_router(), route registration
│ │ ├── state.rs # AppState (service, task_store, instance_id)
│ │ └── routes/ # memory, admin, governance, plugins, sessions
│ ├── memoria-mcp/ # MCP server (stdio/SSE transport)
│ ├── memoria-cli/ # CLI binary: init, mcp, serve, plugin, benchmark
│ ├── memoria-embedding/ # Embedding + LLM client
│ └── memoria-git/ # Git-for-Data: snapshots, branches, merge
├── Cargo.toml # Workspace deps
└── build.rs # Proto compilation (tonic)
Key Traits
trait GovernanceStrategy: Send + Sync {
fn strategy_key(&self) -> &str;
async fn plan(&self, store, task) -> Result<GovernancePlan>;
async fn execute(&self, store, task, plan) -> Result<GovernanceExecution>;
}
trait GovernanceStore: Send + Sync {
async fn list_active_users(&self) -> Result<Vec<String>>;
async fn quarantine_low_confidence(&self, user) -> Result<i64>;
// ... cleanup/maintenance methods
}
trait DistributedLock: Send + Sync {
async fn try_acquire(&self, key, holder, ttl) -> Result<bool>;
async fn renew(&self, key, holder, ttl) -> Result<bool>;
async fn release(&self, key, holder) -> Result<()>;
}
trait AsyncTaskStore: Send + Sync {
async fn create_task(&self, task) -> Result<()>;
async fn complete_task(&self, task_id, result) -> Result<()>;
async fn fail_task(&self, task_id, error) -> Result<()>;
async fn get_task(&self, task_id) -> Result<Option<AsyncTask>>;
}
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.
- 1mo ago First seen · 160 lines · 33 tokens per session scan A 36f145581ad1
architecture is a skill published in the GitHub repository matrixorigin/memoria (614 stars, last pushed yesterday), licensed Apache-2.0. It adds 33 tokens to every session and 1,908 once invoked, about $0.0001 per session on Opus 5.5. 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
sensors-add-skill
Use when registering or adding a new sensor type to the telemetry system's registry, codegen, migrations, and changelog.
review-prs
Review a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks…
fix-failing-tests
Diagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a…
stale-sweep
Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
triage-issues
Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…