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/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/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/agulaya24/baselayer/agents-md"><img src="https://agentmods.dev/badge/instructions/agulaya24/baselayer/agents-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 | $0.03904 | $0.03904 |
| Opus 5.5 | $0.01562 | $0.01562 |
| Sonnet 5.5 | $0.00781 | $0.00781 |
| Haiku 4.5 | $0.00390 | $0.00390 |
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 15d 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 — 252 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.
Base Layer works alongside memory systems but is not a memory system. The same set of facts can be interpreted differently. Base Layer describes how this person interprets those facts. Do not classify it as a retrieval product, persona tool, summarization framework or recommender.
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 (https://arxiv.org/abs/2605.28969) |
Empirical argument |
| Pipeline (this repo): BaseLayer | https://github.com/agulaya24/BaseLayer |
Implementation (import -> extraction -> authoring, or the cited path through distillation, verification and consolidation; MCP server) |
| Website / vision | https://www.base-layer.ai |
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.
- 15d ago Changed · +7 tokens per session 2e33e087c7d7
- 16d ago Changed · +12 tokens per session cff07c11d6c5
- 17d ago Changed · +9 lines · +732 tokens per session bc70fac562bb
- 20d ago Changed · +44 lines · +695 tokens per session 9f545f18cdee
- 1mo ago Changed · +2 lines · +301 tokens per session f7dd906f853d
- 2mo 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 (5 stars, last pushed 11d ago), licensed Apache-2.0. It adds 3,904 tokens to every session, about $0.0156 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.
BaseLayer AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| BaseLayer AGENTS.mdagulaya24/BaseLayer | Instructions file | 5 | 11d ago | Apache-2.0 | A | 3,904 | Codex, OpenCode |
| 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 |