Borrowing it
Nothing to install: this file belongs to stratalab/strata-core. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/stratalab/strata-core/main/CLAUDE.mdgit 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/instructions/stratalab/strata-core/claude-md)<a href="https://agentmods.dev/instructions/stratalab/strata-core/claude-md"><img src="https://agentmods.dev/badge/instructions/stratalab/strata-core/claude-md/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/instructions/stratalab/strata-core/claude-md"><img src="https://agentmods.dev/badge/instructions/stratalab/strata-core/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.03431 | $0.03431 |
| Opus 5.5 | $0.01372 | $0.01372 |
| Sonnet 5.5 | $0.00686 | $0.00686 |
| Haiku 4.5 | $0.00343 | $0.00343 |
Grade A, and why
strata-core CLAUDE.md 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strata-Core: Claude Code Instructions
Status
The V1 architecture is the product. main carries the V1 line; the v1 integration branch has been promoted and retired. Pre-V1 code exists only in git history — do not resurrect it.
Workspace version is inherited from [workspace.package] in the root Cargo.toml — read it there rather than trusting a number restated here, which is how this line came to claim 1.0.0 two releases after that was true (#3133). Publish names are decided: stratadb (embedded-library facade crate) and strata-cli (the strata binary). All crates remain publish = false; note this means the crate the README tells people to depend on is not on crates.io (#3144).
The V1 line is a clean break. No compatibility shims between old and new code, no migration tooling for pre-V1 databases, no parallel old/new paths held alive indefinitely. Opening a pre-V1 database directory fails with failed_precondition.engine.layout_version.
V1 Stack
core
→ storage
→ engine
→ executor / CLI / SDK / Strata AI
→ inference
intelligenceis NOT in this stack — milestone M8 is DEFERRED (decided 2026-09-07, #3171). There is nocrates/intelligenceand there never was one in the V1 line. The layer was designed, scheduled as M8, and deferred with no target release; the design is retained inintelligence-architecture.mdas the starting point if it is ever built (#3136, #3166).Anything below that reads like a rule about it describes that deferred design, not code you can call. Do not write against it.
- core — smallest shared atoms (
BranchId,CommitVersion, timestamp, type-local validation errors). NoValue, noEntityRef, no storage transaction IDs. - storage — generic persistence mechanics, L1-L9 layered. Knows nothing about KV/JSON/event/vector/graph semantics.
- engine — product semantics, data capabilities, branches, time travel, retrieval, IPC classification, clone artifacts, derived-state manifests. Owns adapter traits used by intelligence.
- intelligence — (designed, not built) autoembedding, query expansion, reranking, RAG, generation orchestration. The intended shape is: consumes engine surfaces, never imports storage, never speaks provider HTTP. No crate implements it in 1.2.x; inference is invoked directly from executor behind a feature flag.
- inference — provider execution and model artifact resolution.
Generator/Embedder/Rerankertraits. Knows nothing about Strata databases. - executor / CLI / SDK / Strata AI — consume engine. Never import storage directly. (The rule against importing inference directly describes the intended end state; today executor reaches inference behind a feature flag, because the intelligence layer that was to mediate it does not exist.)
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 Changed · -2 tokens per session 76822496ec7e
- 1mo ago Changed · +22 lines · +533 tokens per session 12748f0291de
- 1mo ago First seen · 243 lines · 2,900 tokens per session scan A 486e5fa30034
strata-core CLAUDE.md is an instructions file published in the GitHub repository stratalab/strata-core (3 stars, last pushed 20d ago), licensed Apache-2.0. It adds 3,431 tokens to every session, about $0.0137 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).