What is BaseLayer CLAUDE.md?

A project-specific instruction file for the Base Layer repository, a system that turns a person’s writing into a structured description of how they interpret information and make decisions. It explains the project background, expected writing style, and common commands for Claude Code.

Use it when working on Base Layer’s text-processing pipeline, examples, debugging, or local memory-server connection.

It gives an AI agent the repository’s context and working rules so it can handle tasks consistently.

How agulaya24/BaseLayer configures Claude Code

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/agulaya24/BaseLayer/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/agulaya24/BaseLayer

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/agulaya24/baselayer/claude-md/github.svg)](https://agentmods.dev/instructions/agulaya24/baselayer/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/agulaya24/baselayer/claude-md"><img src="https://agentmods.dev/badge/instructions/agulaya24/baselayer/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/agulaya24/baselayer/claude-md"><img src="https://agentmods.dev/badge/instructions/agulaya24/baselayer/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,927 This file is loaded in full into every session.

When invoked 3,927 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.03927	$0.03927
Opus 5.5	$0.01571	$0.01571
Sonnet 5.5	$0.00785	$0.00785
Haiku 4.5	$0.00393	$0.00393

Measured 16d ago against content hash 905c409b2b03, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 16d 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.

CLAUDE.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 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 structured document in three layers 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.
Write for a technical product owner: someone who directs the architecture and evaluates results, rather than someone who reads every line of code.

Read the full file on GitHub · 146 lines

Changes

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.

16d ago Changed · +7 tokens per session 905c409b2b03
17d ago Changed · +2 lines · +520 tokens per session 0efca011bd4b
20d ago Changed · +8 lines · +637 tokens per session 90dad0aff3f8
1mo ago Changed · +193 tokens per session 6fdc5f9e7f53
2mo ago First seen · 136 lines · 2,570 tokens per session scan A 883e9422afb1

Subscribe to this mod's changes

BaseLayer CLAUDE.md is an instructions file published in the GitHub repository agulaya24/BaseLayer (5 stars, last pushed 11d ago), licensed Apache-2.0. It adds 3,927 tokens to every session, about $0.0157 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.

Memory and context ai-memory ai-personalization llm-tools mcp-server user-modeling

BaseLayer CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
BaseLayer CLAUDE.mdagulaya24/BaseLayer	Instructions file	5	11d ago	Apache-2.0	A	3,927	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

BaseLayer: Instructions file for Claude Code