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/aemsites/author-kit/agents-mdgit clone --depth 1 https://github.com/aemsites/author-kitWhat 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 | $0.01783 | $0.01783 |
| Opus 5 | $0.00892 | $0.00892 |
| Sonnet 5 | $0.00357 | $0.00357 |
| Haiku 4.5 | $0.00178 | $0.00178 |
Grade A, and why
author-kit 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 2d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to coding agents when working with code in this repository.
What this is
Author Kit is a template repo for AEM Edge Delivery / DA-authored sites. Content is authored in
da.live; this repo is the code half. README.md lists the authoring features and design tokens —
read it for the content-side vocabulary.
When something here looks arbitrary, check docs/adr/ before changing it — that is where decisions
the code cannot explain are recorded, and docs/adr/README.md says when a new one is warranted.
Designs for larger bodies of work live in docs/specs/NNN-topic/.
What you own
Everything except scripts/ak.js. It's the shared engine — nearly 400 lines that every fork
inherits — so changes belong upstream, in a GitHub issue with your use case, not in your project.
Prefer solving it in a file that's yours: getting a change into lazy.js (~25 lines) is a far
smaller ask than one into ak.js. Project configuration goes in scripts/scripts.js, which is the
seam for exactly this.
That rule is for projects built from this template. In this repo you are the maintainer — ak.js
is fair game, but every change ships to every downstream fork, so weigh the blast radius rather
than the permission.
Buildless — every line ships
There is no bundler or transpiler. Files are served to the browser exactly as they are on disk
(head.html loads /styles/styles.css and /scripts/scripts.js as native ESM). Consequences:
- Editorial comments, dead code, and defensive scaffolding are shipped bytes. Keep code terse.
- Browser support is live at HEAD too. Baseline Newly available is the bar: a feature qualifies
once it ships in the current stable release of every core browser, mobile Safari and Firefox for
Android included. No polyfills, no
@supportsfallbacks, no build-time transforms. deps/holds vendored third-party code (lit, rum) and is eslint-ignored.npm run build:litis the one build step, and only for that dependency.- Every static import is its own blocking request before first paint, so anything statically
reachable from
scripts.jssits on the LCP critical path. Keep that set minimal and reach for dynamicimport()instead, the waylazy.js,svg.js, anderror.jsare pulled in.
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.
- 2d ago First seen · 128 lines · 1,783 tokens per session scan A ba81f179ce7a
author-kit AGENTS.md is an instructions file published in the GitHub repository aemsites/author-kit (12 stars, last pushed 19d ago), licensed Apache-2.0. It adds 1,783 tokens to every session, about $0.0089 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 2026-08-30.
Other instructions, from other repositories
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.
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).
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.