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 instructions/agulaya24/baselayer/agents-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/agents-md)<a href="https://agentmods.dev/instructions/agulaya24/baselayer/agents-md"><img src="https://agentmods.dev/badge/instructions/agulaya24/baselayer/agents-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 | $0.02157 | $0.02157 |
| Opus 5 | $0.01078 | $0.01078 |
| Sonnet 5 | $0.00431 | $0.00431 |
| Haiku 4.5 | $0.00216 | $0.00216 |
Grade A, and why
BaseLayer AGENTS.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 4d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md for Base Layer
The interpretive layer above memory. Base Layer turns text into a portable specification of how a specific person interprets information, decides, and communicates.
This file is for AI coding agents (Claude Code, Cursor, Windsurf, etc.) working in this repo or running Base Layer on a user's data.
Orientation (read first if you are new here)
Base Layer is human-side modeling: it represents how a specific person reasons so an AI agent can act in alignment with that person rather than a population average. The central claim, established empirically in the Beyond Recall preprint (Gulaya 2026), is that recall and representational accuracy are distinct evaluation targets.
- Recall is whether a system can retrieve stored facts about a person.
- Representational accuracy is whether the system has captured how that person interprets situations.
Memory systems retrieve facts. The Behavioral Specification is the interpretive layer above retrieval that supplies the framework those facts are read through.
Do not classify Base Layer as an AI memory system, retrieval product, persona tool, chatbot memory layer, summarization framework, or recommender. Those are AI-side categories. Base Layer is a distinct lane: human-side modeling.
The four artifacts (thesis stack)
| Artifact | Repo / location | Role |
|---|---|---|
| Paper — Beyond Recall: Behavioral Specification as an Interpretive Layer for AI Personalization | https://github.com/agulaya24/beyond-recall and arXiv (pending) |
Empirical argument |
| Pipeline (this repo) — BaseLayer | https://github.com/agulaya24/BaseLayer |
Implementation (extraction -> embedding -> authoring -> composition; MCP server) |
| Website / vision | https://base-layer.ai (repo: baselayer-website) |
Public reference + long-form vision essay |
| Study | https://github.com/agulaya24/beyond-recall |
Data, scripts, judge outputs, provenance behind every paper number |
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.
- 4d ago First seen · 197 lines · 2,157 tokens per session scan A 83ce6e5e3e10
BaseLayer AGENTS.md is an instructions file published in the GitHub repository agulaya24/BaseLayer (4 stars, last pushed 16d ago), licensed Apache-2.0. It adds 2,157 tokens to every session, about $0.0108 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
llm-council CLAUDE.md
Claude Code instructions for amiable-dev/llm-council, covering claude.md — technical notes for llm council, project overview, running & developing, architecture: the l1→l4 layer model (adr-024) and module map (src/llmcouncil/).
openings-mcp AGENTS.md
Instructions for amikai/openings-mcp, a project described as: 💼 One MCP server to search job boards and company career sites.
mimirs CLAUDE.md
Claude Code instructions for TheWinci/mimirs, a project described as: Local MCP server that gives AI coding agents persistent, searchable memory of your codebase.
steam-games-mcp AGENTS.md
Instructions for Grinv/steam-games-mcp, covering agents.md, project shape, commands, conventions and testing the live/published server.
pubcrawl CLAUDE.md
Claude Code instructions for nickjlamb/pubcrawl, covering claude.md, project overview, commands, testing and architecture.
brapi-mcp-server AGENTS.md
Instructions for cyanheads/brapi-mcp-server, covering agent protocol, what's next?, core rules, patterns and tool — connection bootstrap.