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/aontu-lang/aontu/agents-mdgit clone --depth 1 https://github.com/aontu-lang/aontuWrote 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/aontu-lang/aontu/agents-md)<a href="https://agentmods.dev/instructions/aontu-lang/aontu/agents-md"><img src="https://agentmods.dev/badge/instructions/aontu-lang/aontu/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 | $0.07591 | $0.07591 |
| Opus 5 | $0.03795 | $0.03795 |
| Sonnet 5 | $0.01518 | $0.01518 |
| Haiku 4.5 | $0.00759 | $0.00759 |
Grade A, and why
aontu 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 — 565 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aontu — agent & contributor guide
Aontu is a JSON structure unifier (a purpose-specific dialect inspired by CUE). This repository ships two implementations kept in parity:
- TypeScript in
ts/— the canonical implementation. - Go in
go/— a port that mirrors the TypeScript semantics.
Three decisions govern everything below and are recorded in
ADR.md: ADR-001 (the two implementations stay at full
parity, proved by the shared spec), ADR-002 (coverage stays at
100 % in both, with every exclusion justified in the source), and
ADR-003 (where a host subsystem supplies semantics, Aontu defines
the meaning and rewrites the input rather than trusting the host). Read
those before proposing a change that touches one implementation only,
that adds code no test reaches, or that hands a value to a host library
to interpret.
The structural layout follows voxgig/util:
top-level ts/ and go/ siblings and a fan-out Makefile. On top of
that, this repo adds a shared, data-driven test suite so both
implementations are checked against the same cases.
CI note: the workflow lives at
.github/workflows/build.ymland runs three jobs —build-ts,build-go, andcoverage(the ADR-002 floor). Editing anything under.github/workflows/needs the GitHubworkflowOAuth scope, so a push that touches it must come from an account that has the scope.
Repository layout
.
├── ADR.md # architecture decision record (the fundamentals)
├── AGENTS.md # this file
├── CLAUDE.md # pointer to AGENTS.md
├── Makefile # fans out to ts/ and go/
├── README.md
├── docs/
│ ├── design/ # design notes — the why behind settled decisions
│ ├── lsp.md # language server reference
│ └── shared-spec.md # the shared TSV test format
├── editors/ # editor plugins (VS Code, Emacs, Vim) → aontu-lsp
├── test/
│ └── spec/ # shared test cases — *.tsv (language-agnostic)
│ └── divergent.tsv # the parity ledger (commentary only, no rows)
├── ts/ # canonical TypeScript implementation
│ ├── package.json # `bin`: aontu -> bin/aontu.js, aontu-lsp -> bin/aontu-lsp.js
│ ├── src/ # source incl. cli.ts, lsp.ts, lsp-server.ts (+ src/tsconfig.json -> ../dist)
│ ├── test/ # tests (+ test/tsconfig.json -> ../dist-test)
│ ├── dist/ # committed compiled JS + .d.ts (incl. cli.js)
│ └── dist-test/ # committed compiled tests (the run target)
└── go/ # Go port
├── go.mod # module github.com/aontu-lang/aontu/go
├── *.go # package aontu (incl. check.go: Check -> []Problem)
├── lsp/ # LSP library (Diagnostics + Handler)
├── cmd/aontu/ # `aontu` CLI (package main, file/stdin/REPL)
├── cmd/aontu-lsp/ # `aontu-lsp` Language Server (stdio)
├── aontu_test.go # Go-native sanity tests
└── spec_test.go # runs the shared test/spec/*.tsv suite
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 · +22 lines · +329 tokens per session 26aeda326c3d
- 4d ago First seen · 543 lines · 7,262 tokens per session scan A e8689c65dff4
aontu AGENTS.md is an instructions file published in the GitHub repository aontu-lang/aontu (10 stars, last pushed today), licensed MIT. It adds 7,591 tokens to every session, about $0.0380 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.