Borrowing it
Nothing to install: this file belongs to arturseo-geo/llm-knowledge-base. 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/arturseo-geo/llm-knowledge-base/main/AGENTS.mdgit clone --depth 1 https://github.com/arturseo-geo/llm-knowledge-baseWrote 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/arturseo-geo/llm-knowledge-base/agents-md)<a href="https://agentmods.dev/instructions/arturseo-geo/llm-knowledge-base/agents-md"><img src="https://agentmods.dev/badge/instructions/arturseo-geo/llm-knowledge-base/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/arturseo-geo/llm-knowledge-base/agents-md"><img src="https://agentmods.dev/badge/instructions/arturseo-geo/llm-knowledge-base/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 | $0.03028 | $0.03028 |
| Opus 5.5 | $0.01211 | $0.01211 |
| Sonnet 5.5 | $0.00606 | $0.00606 |
| Haiku 4.5 | $0.00303 | $0.00303 |
Grade A, and why
llm-knowledge-base 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 2mo 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — LLM Knowledge Base Schema
Version: 1.1.0 | Status: Stable | Last updated: 2026-04-06
This file is the single source of truth for any LLM agent operating on this knowledge base. It defines the directory structure, file conventions, operational rules, and quality standards the agent must follow. The agent reads this file at the start of every session.
1. Repository layout
/
├── AGENTS.md ← this file (agent reads first, always)
├── raw/ ← source material, never edited by agent
│ ├── articles/
│ ├── papers/
│ ├── repos/
│ ├── datasets/
│ └── images/
├── wiki/ ← LLM-compiled knowledge base (agent owns this)
│ ├── _index.md ← master index: one line per article, always kept current
│ ├── _concepts.md ← flat list of all named concepts with one-line definitions
│ ├── _graph.md ← adjacency list of concept→concept links
│ ├── concepts/ ← one .md per named concept
│ ├── summaries/ ← one .md per raw/ source document
│ └── topics/ ← topic-level overview articles (cross-concept)
├── insights/ ← human-written notes only. Agent never writes here.
│ └── *.md ← your own thinking: observations, connections, questions
├── output/ ← query results, slides, charts (agent writes, human reads)
│ ├── reports/
│ ├── slides/ ← Marp .md files
│ └── figures/ ← matplotlib .png files
└── learning/ ← structured learning layer (agent writes, human reviews)
├── _review.md ← spaced repetition queue: concept, due date, interval, ease
├── flashcards/ ← one .md per concept with Q&A pairs
└── gaps.md ← detected knowledge gaps and open questions
2. Agent identity and scope
The agent is the sole author and maintainer of everything under wiki/, output/, and learning/. The human never edits these directories directly.
The agent never modifies anything under raw/ or insights/. Raw files are immutable source inputs. Insights files are immutable human outputs — your own thinking, not the agent's synthesis.
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.
- 2mo ago First seen · 290 lines · 3,028 tokens per session scan A f222f63b4cb7
llm-knowledge-base AGENTS.md is an instructions file published in the GitHub repository arturseo-geo/llm-knowledge-base (41 stars, last pushed 7mo ago), licensed MIT. It adds 3,028 tokens to every session, about $0.0121 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 2026-08-30.
llm-knowledge-base AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| llm-knowledge-base AGENTS.mdarturseo-geo/llm-knowledge-base | Instructions file | 41 | 7mo ago | MIT | A | 3,028 | 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 | today | 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 |