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/ambystechcom/ambykit/claude-mdgit clone --depth 1 https://github.com/ambystechcom/AmbyKitWhat 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 | $0.00257 | $0.00257 |
| Opus 5 | $0.00129 | $0.00129 |
| Sonnet 5 | $0.00051 | $0.00051 |
| Haiku 4.5 | $0.00026 | $0.00026 |
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.
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.*.mdand are generated fromsrc/prompts/— edit the neutral prompt, not the command file, thenambykit sync. - When you finish a nontrivial change, run
npm run typecheckandnpm testbefore committing. - Keep this repo self-hosted: after changing
src/templates/orsrc/prompts/, regenerate the repo's own tool files withambykit sync(once the CLI exists) so.claude/stays current.
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 · 18 lines · 257 tokens per session scan A ff29a64d58b4
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.
Other instructions, from other repositories
thinkrail AGENTS.md
Instructions for JetBrains/thinkrail, covering thinkrail, module structure & boundaries (top-priority requirement), engine: pi only, in-process, architecture (three rings) and repo layout.
truthmark AGENTS.md
Instructions for merlinhu1/truthmark, covering authority, documentation scope, product boundary, rules and instruction surface boundary.
thinkrail CLAUDE.md
Instructions for JetBrains/thinkrail, a project described as: Vibe code with pi in a lightweight, real IDE - The Vibe You Need.
truthmark CLAUDE.md
Instructions for merlinhu1/truthmark, covering authority, documentation scope, product boundary, rules and instruction surface boundary.
cctop AGENTS.md
Instructions for st0012/cctop, covering agents.md - development guide for cctop, scope and sources, required development rules, driver workflow and github and pr rules.
examples CLAUDE.md
Claude Code instructions for rossoctl/examples, covering claude.md - agent examples, repository structure, key commands, code style and dco sign-off (mandatory).