Borrowing it
Nothing to install: this file belongs to agent-sh/agnix. 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/agent-sh/agnix/main/AGENTS.mdgit clone --depth 1 https://github.com/agent-sh/agnixWrote 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/agent-sh/agnix/agents-md)<a href="https://agentmods.dev/instructions/agent-sh/agnix/agents-md"><img src="https://agentmods.dev/badge/instructions/agent-sh/agnix/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/agent-sh/agnix/agents-md"><img src="https://agentmods.dev/badge/instructions/agent-sh/agnix/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 | $0.02075 | $0.02075 |
| Opus 5.5 | $0.00830 | $0.00830 |
| Sonnet 5.5 | $0.00415 | $0.00415 |
| Haiku 4.5 | $0.00208 | $0.00208 |
Grade A, and why
agnix 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 today.
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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Memory: agnix
Linter for agent configurations. Validates Skills, Hooks, MCP, Memory, Plugins.
Repository: https://github.com/agent-sh/agnix
Rules
knowledge-base/rules.jsonis the source of truth for rules. A new rule goes into bothrules.jsonandknowledge-base/VALIDATION-RULES.md; CI parity tests fail when they drift. See "Adding a rule" below.- Output is plain text: no emojis, no ASCII art.
- Certainty levels: HIGH (>95%), MEDIUM (75-95%), LOW (<75%).
- Release binaries are compiled with LTO and stripped.
- Track work in GitHub issues.
- A feature or fix is done when a test covers it.
- Long-form docs live in
README.md,SPEC.mdandknowledge-base/(especiallyknowledge-base/VALIDATION-RULES.md). This file holds agent instructions only. Create no summary, plan or scratch docs unless the task needs them. - Wait for the
revuto-reviewcheck to pass before merging: it is the most thorough review. If revuto is capped or unavailable, do not wait; a self-review is enough, noted in the PR body. - Address every review comment before merging, minor ones included. If you disagree, reply in the review thread.
- In prose, write a spaced single dash (
-), not--. CLI flags like--helpor--fixare fine.
Architecture
Crate dependency graph
agnix-rules (data-only, generated from rules.json)
↓
agnix-core (validation engine)
↓
├── agnix-cli (command-line interface)
├── agnix-lsp (language server protocol)
├── agnix-mcp (MCP server)
└── agnix-wasm (WebAssembly bindings)
Project layout
crates/
├── agnix-rules/ # Rule definitions (build-time generated)
├── agnix-core/ # Core: parsers, schemas, validators, diagnostics
├── agnix-cli/ # CLI binary (clap)
├── agnix-lsp/ # LSP server (tower-lsp, tokio)
├── agnix-mcp/ # MCP server (rmcp)
└── agnix-wasm/ # WASM bindings for browser/runtime integrations
editors/
├── neovim/ # Neovim plugin
├── vscode/ # VS Code extension
├── jetbrains/ # JetBrains IDE plugin
└── zed/ # Zed extension
knowledge-base/ # 757 rules, 75+ sources, rules.json
tests/fixtures/ # Test cases by category
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.
- today Changed · -11 tokens per session 3f9ba9f998a4
- yesterday Changed · -4 lines · +42 tokens per session eb875ee33910
- 12d ago Changed · +2 lines · +24 tokens per session 596f9ae87cd5
- 21d ago Changed 34640062bd28
- 24d ago Changed · -109 lines · -929 tokens per session 7466a3c26d8d
- 25d ago Changed · +15 lines · +199 tokens per session 2b0bf0b25852
- 1mo ago Changed 8499202b015f
- 1mo ago Changed · +8 lines · +42 tokens per session a5282d0577f8
- 1mo ago Changed 440af8582459
- 1mo ago First seen · 225 lines · 2,708 tokens per session scan A 5331d94e38f2
agnix AGENTS.md is an instructions file published in the GitHub repository agent-sh/agnix (463 stars, last pushed today), licensed Apache-2.0. It adds 2,075 tokens to every session, about $0.0083 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.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.