Borrowing it
Nothing to install: this file belongs to agulaya24/BaseLayer. 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/agulaya24/BaseLayer/main/CLAUDE.mdgit clone --depth 1 https://github.com/agulaya24/BaseLayerWrote 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/agulaya24/baselayer/claude-md)<a href="https://agentmods.dev/instructions/agulaya24/baselayer/claude-md"><img src="https://agentmods.dev/badge/instructions/agulaya24/baselayer/claude-md.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 | $0.02570 | $0.02570 |
| Opus 5 | $0.01285 | $0.01285 |
| Sonnet 5 | $0.00514 | $0.00514 |
| Haiku 4.5 | $0.00257 | $0.00257 |
Grade A, and why
BaseLayer 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 6d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Claude Code-specific guide for working in the Base Layer repo. This file complements AGENTS.md (provider-neutral) with Claude Code harness specifics.
For background on the project, read AGENTS.md and README.md first. This file is shorter on purpose.
Project context
Base Layer is the interpretive layer above memory. The pipeline takes text (conversations, journals, essays, books) and produces a behavioral specification: a 5,000 to 10,000 token structured document that captures how a specific person interprets information, decides, and communicates. Memory systems retrieve facts. The specification supplies the framework those facts are read through.
If you are running in this repo as Claude Code, you are most likely doing one of four things:
- Running the pipeline on the user's text data (ChatGPT export, journal directory, document corpus).
- Debugging extraction, authoring, or composition (a stage produced too few facts, a layer regenerated wrong, etc.).
- Exploring example specifications under
examples/to understand the output format. - Connecting the local MCP server to inject the specification into a Claude conversation.
If the user's request is ambiguous, ask before running anything that spends API budget.
Voice and prose constraints
When you generate user-facing text in this repo (commit messages, doc edits, blog drafts, paper edits, recipes, comments in source), follow the project's voice constraints:
- No em-dashes. Restructure sentences. Do not substitute hyphens.
- No GTM language ("beats", "crushes", "outperforms", "wins"). Scientific framing only.
- Canonical terms: "interpretive layer" and "specification" body-primary. "Behavioral specification" on first mention. Do not use "behavioral compression" or "identity model" in new prose.
- No marketing prose. Action-first. Direct.
- Aarik wrote the project. He does not write code; he architects and directs. Write for an audience of one technical product owner.
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.
- 6d ago First seen · 136 lines · 2,570 tokens per session scan A 883e9422afb1
BaseLayer CLAUDE.md is an instructions file published in the GitHub repository agulaya24/BaseLayer (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,570 tokens to every session, about $0.0128 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 2026-08-31.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.