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/stratalab/strata-core/agentsnpx skills add stratalab/strata-core --skill agentsgit clone --depth 1 https://github.com/stratalab/strata-coreWrote 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/stratalab/strata-core/agents)<a href="https://agentmods.dev/skills/stratalab/strata-core/agents"><img src="https://agentmods.dev/badge/skills/stratalab/strata-core/agents.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00076 | $0.01450 |
| Opus 5 | $0.00038 | $0.00725 |
| Sonnet 5 | $0.00015 | $0.00290 |
| Haiku 4.5 | $0.00008 | $0.00145 |
Grade A, and why
strata 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 2d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
StrataDB {version}
StrataDB is an embedded database: it runs inside the process against a local directory, like SQLite or DuckDB — no server, no port, no connection string. One database holds five data primitives on one branch-aware, time-travelling substrate. This skill matches strata {version}; the binary and the wheel are self-describing (see "Deeper reference" below).
Open a database (Python)
import stratadb
db = stratadb.open("./mydb") # durable directory (created if absent)
db = stratadb.open(cache=True) # ephemeral, in-memory
db = stratadb.from_env() # path from $STRATA_DB
Never rely on the current directory — stratadb.open() with no target raises
invalid_argument.cli.no_database. Use a context manager or db.close().
Choose a primitive
| Data shape | Use | Namespace |
|---|---|---|
| Opaque value by key | key-value | db.kv — values are bytes; str encodes as UTF-8 |
| Structured record, addressed by field | JSON documents | db.json — read/write inside a doc by path ("$.name") |
| Embeddings, similarity search | vectors | db.vectors — collections fix dimension + metric |
| Ordered, append-only history | events | db.events — hash-chained; count is len() |
| Relationships, traversal, analytics | graph | db.graphs — both edge endpoints must exist first |
db.kv.put("greeting", "hello"); db.kv.get("greeting") # b"hello"
db.json.set("user:1", "$", {"name": "Ada"}); db.json.get("user:1", "$.name")
db.vectors.create_collection("notes", dimension=384)
db.vectors.upsert("notes", "n1", vec, metadata={"kind": "note"})
db.vectors.query("notes", query_vec, k=5)
db.events.append("deploy", {"ok": True})
db.graphs.create("g"); db.graphs.add_node("g", "a"); db.graphs.add_node("g", "b")
db.graphs.add_edge("g", "a", "link", "b")
Branches and time travel
Every primitive is branch-aware. A fork is cheap and isolates writes; the
default branch is named default (not main):
db.branches.fork("default", "experiment")
exp = db.at(branch="experiment") # scoped view over the same handle
exp.kv.put("k", "risky-value")
db.kv.get("k") # None on default — isolated
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.
- 2d ago First seen · 131 lines · 76 tokens per session scan A 8d3728090a26
strata is a skill published in the GitHub repository stratalab/strata-core (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 76 tokens to every session and 1,450 once invoked, about $0.0004 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 2026-09-04.
Other skills, from other repositories
qdrant
Vector search engine for production RAG systems.
chroma
Embedding database for RAG and semantic search.
pinecone
Managed vector DB for production RAG and search.
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
pgvector-semantic-search
Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. Trigger when user asks to: Store or search vector embeddings in PostgreSQL Set up semantic search, similarity search, or nearest neighbor search Create HNSW or IVFFlat indexes for vectors…