AmbyKit CLAUDE.md

Project instructions for Claude Code in the AmbyKit repository, including its shared guidance, slash commands, generated files, and required checks.

In plain words
What is it for?
Use them when changing AmbyKit prompts or templates, syncing its command files, and running type checks and tests.
Why use it?
They explain which files to edit, how to regenerate Claude-specific tools, and which tests to run before committing.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/ambystechcom/ambykit/claude-md
Clone the repo
git clone --depth 1 https://github.com/ambystechcom/AmbyKit
Per session 257 This file is loaded in full into every session.
When invoked 257 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00257 $0.00257
Opus 5 $0.00129 $0.00129
Sonnet 5 $0.00051 $0.00051
Haiku 4.5 $0.00026 $0.00026

Measured 2d ago against content hash ff29a64d58b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AmbyKit CLAUDE.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.

CLAUDE.md · 18 lines

What it actually says

@AGENTS.md

Claude Code — notes for the AmbyKit repo

The shared, tool-neutral guidance is in @AGENTS.md above (imported). This file adds only Claude-Code-specific notes. Claude Code does not read AGENTS.md natively — the @AGENTS.md import on the first line is the bridge, so keep it there.

Claude-specific

  • The AmbyKit workflow is available here as slash commands under /amby.* (e.g. /amby.specify, /amby.design, /amby.plan, /amby.tasks). These live in .claude/commands/amby.*.md and are generated from src/prompts/ — edit the neutral prompt, not the command file, then ambykit sync.
  • When you finish a nontrivial change, run npm run typecheck and npm test before committing.
  • Keep this repo self-hosted: after changing src/templates/ or src/prompts/, regenerate the repo's own tool files with ambykit sync (once the CLI exists) so .claude/ stays current.
Changes

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.

  1. 2d ago First seen · 18 lines · 257 tokens per session scan A ff29a64d58b4

Subscribe to this mod's changes

AmbyKit CLAUDE.md is an instructions file published in the GitHub repository ambystechcom/AmbyKit (2 stars, last pushed 7d ago), licensed MIT. It adds 257 tokens to every session, about $0.0013 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.