amby.plan

A command that turns an approved feature description and interface design into a technical implementation plan.

In plain words
What is it for?
Use it to create plan.md and, when needed, supporting data models, interface contracts, or research notes.
Why use it?
It keeps technology choices, architecture, project phases, and requirements mapping in one documented plan.

Command for Claude Code

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 commands/ambystechcom/ambykit/amby.plan
Clone the repo
git clone --depth 1 https://github.com/ambystechcom/AmbyKit

Made for: Claude Code.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 387 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00016 $0.00387
Opus 5 $0.00008 $0.00193
Sonnet 5 $0.00003 $0.00077
Haiku 4.5 $0.00002 $0.00039

Measured 2d ago against content hash f48b5c86ffdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

amby.plan 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/commands/amby.plan.md · 25 lines

What it actually says

Act as the Architect in @.amby/roles/architect.md and say so in your first line. If $ARGUMENTS contains --as <id>, use @.amby/roles/<id>.md instead; if that file is missing, stop and list the files in .amby/roles/.

Write the implementation plan for feature $ARGUMENTS (default: the current feature).

Context: read that feature's spec.md and ui.md, plus @.amby/constitution.md.

  1. Write plan.md following @.amby/templates/plan.md: technical context (stack, libraries, constraints), architecture, and a phased approach (Phase 0 research → Phase 1 foundation → feature phases).
  2. This is the first artifact with technology decisions. Ensure every choice honors the constitution (cite principle numbers).
  3. Map each FR-###/US-# to how the design satisfies it. Reference by ID — do not restate the spec. Flag any requirement you can't satisfy as a risk.
  4. Generate supporting artifacts only if needed: data-model.md (entities/invariants), contracts/ (API/interface specs), research.md (decisions with rationale).
  5. Do not invent requirements not in the spec; if you find a gap, note it and suggest a clarify.

Keep the plan lean; link to spec/UI rather than duplicating.

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 · 25 lines · 16 tokens per session scan A f48b5c86ffdb

Subscribe to this mod's changes

amby.plan is a command published in the GitHub repository ambystechcom/AmbyKit (2 stars, last pushed 7d ago), licensed MIT. It adds 16 tokens to every session and 387 once invoked, about $0.0001 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.