Borrowing it
Nothing to install: this file belongs to go-to-k/cdkd. 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/go-to-k/cdkd/main/AGENTS.mdgit clone --depth 1 https://github.com/go-to-k/cdkdWrote 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/go-to-k/cdkd/agents-md)<a href="https://agentmods.dev/instructions/go-to-k/cdkd/agents-md"><img src="https://agentmods.dev/badge/instructions/go-to-k/cdkd/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/go-to-k/cdkd/agents-md"><img src="https://agentmods.dev/badge/instructions/go-to-k/cdkd/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 | $0.03009 | $0.03009 |
| Opus 5.5 | $0.01204 | $0.01204 |
| Sonnet 5.5 | $0.00602 | $0.00602 |
| Haiku 4.5 | $0.00301 | $0.00301 |
Grade C, and why
cdkd AGENTS.md scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
zip, a link, `pip install <x>`, `npm i <x>`, `curl … | sh` or an inline Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
zip, a link, `pip install <x>`, `npm i <x>`, `curl … | sh` or an inline How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
cdkd (CDK Direct) is a drop-in CDK CLI for existing CDK apps — up to 15x faster deploys via direct AWS SDK and Cloud Control API calls instead of CloudFormation. It complements the AWS CDK CLI rather than replacing it: cdkd for dev/test iteration, the AWS CDK CLI in production for full CloudFormation tooling. It is for dev/test workflows only — early in development, not yet production-ready.
This file carries only what an agent must know before it reads a file or
runs a command. Everything else lives beside the code it governs, in
.claude/rules/*.md — each declares a paths: glob naming the files it
applies to. Claude Code loads a rule automatically when a matching file is
read; any other agent should read the matching rule itself before changing
those files. The table at the end maps subject to file. .claude/skills/* are
Claude Code workflows, invoked as /<name>; their steps are readable as plain
Markdown by anything else.
Build and test
vp run build # required after any src/ change — the user runs node dist/cli.js
vp test run # preferred over `vp run test`: no task runner between caller and verdict
vp run typecheck | lint | lint:fix | format | format:check
Tasks are registered in vite.config.ts and invoked as vp run <task> — there
is no package.json scripts block. Setup and the full task list:
CONTRIBUTING.md.
Conventions
- ESM:
"type": "module", so every relative import carries the.jsextension even in TypeScript —from './bar.js', neverfrom './bar'. - Add unit tests with the change, for new functionality and for bug fixes, without being asked.
- A user-visible behavior change writes one changelog entry under
changelog.d/entries/; changelog.d/_header.md is the contract. Agent instructions, tests, CI, hooks and docs write none.
Design principles
Performance is cdkd's defining value: never slow an ordinary deploy, and add no AWS or S3 call a deploy does not need. Then CloudFormation parity: do what the AWS CDK CLI / CloudFormation does. On a separate axis, never ranked below these: no regression, no new plaintext secret or exposure, an error names the cause and the next step, and a schema bump migrates users' S3 state automatically (nothing puts it back). When two conflict, record at the site which gave way and why.
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 00adf3769869
- yesterday Changed c68bb9020ce8
- 9d ago Changed 1eb9728e78e0
- 16d ago Changed · +2 lines · -8 tokens per session 70180d71d457
- 22d ago Changed 501c139e6053
- 28d ago Changed · +4 lines · +83 tokens per session 124b4ac6a6de
- 1mo ago Changed · -109 lines · -6,828 tokens per session scan D → C 5016f61eedf7
- 1mo ago First seen · 298 lines · 9,762 tokens per session scan D 02c78d72bbf2
cdkd AGENTS.md is an instructions file published in the GitHub repository go-to-k/cdkd (156 stars, last pushed today), licensed Apache-2.0. It adds 3,009 tokens to every session, about $0.0120 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-21.
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.