Borrowing it
Nothing to install: this file belongs to sbhooley/ainativelang. 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/sbhooley/ainativelang/main/AGENTS.mdgit clone --depth 1 https://github.com/sbhooley/ainativelangWrote 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/sbhooley/ainativelang/agents-md)<a href="https://agentmods.dev/instructions/sbhooley/ainativelang/agents-md"><img src="https://agentmods.dev/badge/instructions/sbhooley/ainativelang/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/sbhooley/ainativelang/agents-md"><img src="https://agentmods.dev/badge/instructions/sbhooley/ainativelang/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 | $0.09989 | $0.09989 |
| Opus 5.5 | $0.03996 | $0.03996 |
| Sonnet 5.5 | $0.01998 | $0.01998 |
| Haiku 4.5 | $0.00999 | $0.00999 |
Grade A, and why
ainativelang 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 1mo 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 — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Ground Truth for AI Agents
For agents — install AINL (one step)
If you are an AI agent that needs AINL set up in your host stack, run:
pipx install 'ainativelang[mcp]' && ainl setup --auto
Fallback if pipx is unavailable:
python3 -m pip install --user 'ainativelang[mcp]' && ainl setup --auto
That is the entire install. The setup command auto-detects your host
(Claude Code, Cursor, Cline, Codex CLI, Codex Desktop, Claude Desktop,
OpenClaw, Hermes, ArmaraOS, or any generic MCP host), merges the right
MCP server entry into its config, and verifies with ainl doctor.
Existing config files are backed up with a timestamp before any change.
If your host is not detected, run ainl setup --print-config to get a
paste-ready stdio MCP server block.
Machine-readable install spec: .agent-install.json.
Design contract: docs/architecture/2026-05-05-agent-install-simplification.md.
Read this FIRST before doing anything in this repository.
Headline repo stats: If you edit the compiler, runtime, CLI, adapters, tests, or examples, run python scripts/refresh_repo_stats.py or install pre-commit (pre-commit install — see CONTRIBUTING.md) so STATUS.yaml and this file’s Repository Layout stay accurate. CI enforces this on every PR.
What This Repo Is
Python compiler + runtime for AINL (AI Native Language), version 1.8.0.
AINL compiles .ainl source files into an IR (intermediate representation)
graph, then executes that graph via adapters (database, HTTP, LLM, Solana, etc).
Repository Layout
compiler_v2.py — The compiler (7052 lines). Parses .ainl → IR dict.
compiler_diagnostics.py — Error/warning types used by compiler.
runtime/engine.py — The runtime engine (3106 lines). Executes IR graphs.
runtime/adapters/ — Runtime adapter base classes and builtins.
cli/main.py — CLI entry point (3766 lines). All `ainl` commands.
adapters/ — 70 Python files under `adapters/` (recursive); ArmaraOS monitor bootstrap: `armaraos_integration.py`, `armaraos_defaults.py` (`build_armaraos_monitor_registry`, `boot_armaraos_graph_memory`). See `docs/ARMARAOS_INTEGRATION.md`, `docs/adapters/AINL_GRAPH_MEMORY.md`.
armaraos/emitter/ — `armaraos.py`: `ainl emit --target armaraos` Hand pack (`HAND.toml`, IR JSON, `security.json`, README) with `schema_version` for openfang-hands validation.
scripts/ — Standalone scripts (`refresh_repo_stats.py`, emit_langgraph, emit_temporal, `ainl_mcp_server.py` MCP entrypoint, etc).
tooling/ — Graph analysis, normalization, effect analysis; `ainl_get_started.py` (authoring wizard + adapter contracts), `corpus_mining.py` (strict-valid family index for `corpus/strict_valid_family_index.json`).
corpus/ — Generated/mined JSON (e.g. `strict_valid_family_index.json`, `reverse_prompt_fixtures.json`); see `docs/operations/MCP_AINL_WIZARD_AND_CORPUS.md`.
examples/ — 110+ `.ainl` files under `examples/` (strict CI subset: `tooling/artifact_profiles.json`). See `examples/README.md`.
tests/ — 264 `*.py` files under `tests/` (~32k lines total); 234 `test_*.py` modules; pytest —collect-only: 1636/1675 (see STATUS.yaml). Definitions: **`STATUS.yaml`** → `real_and_working.tests`.
docs/ — Documentation (some accurate, some aspirational — see **`STATUS.yaml`**).
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.
- 1mo ago First seen · 399 lines · 9,989 tokens per session scan A 3c3611609461
ainativelang AGENTS.md is an instructions file published in the GitHub repository sbhooley/ainativelang (639 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 9,989 tokens to every session, about $0.0400 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.