amby.revise

amby.revise is a command for Claude Code from ambystechcom/AmbyKit. It costs 23 tokens per session (611 once invoked), scanned A, original, MIT.

A command for continuing an existing feature specification or design document in place. It adds new stories, requirements, and success criteria while preserving the existing numbered items.

In plain words
What is it for?
Use it to refine an existing AmbyKit feature, add scope or requirements, and optionally continue its design.
Why use it?
It prevents an unfinished specification from being regenerated or accidentally changed, and stops edits when the feature is already marked complete.

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.revise
Clone the repo
git clone --depth 1 https://github.com/ambystechcom/AmbyKit

Made for: Claude Code.

Wrote 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.

agentmods badge for amby.revise

README.md
[![agentmods](https://agentmods.dev/badge/commands/ambystechcom/ambykit/amby.revise.svg)](https://agentmods.dev/commands/ambystechcom/ambykit/amby.revise)
Your own site
<a href="https://agentmods.dev/commands/ambystechcom/ambykit/amby.revise"><img src="https://agentmods.dev/badge/commands/ambystechcom/ambykit/amby.revise.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 611 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 $0.00023 $0.00611
Opus 5 $0.00012 $0.00305
Sonnet 5 $0.00005 $0.00122
Haiku 4.5 $0.00002 $0.00061

Measured 4d ago against content hash c12c101d6371, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

amby.revise 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 4d 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.revise.md · 34 lines

What it actually says

Act as the Product Manager in @.amby/roles/pm.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/.

Continue the spec (and, optionally, the design) for feature $ARGUMENTS (default: the current feature).

Context: read only that feature's spec.md (and its ui.md if continuing design) plus the structure of @.amby/templates/spec.md. This command extends an existing feature — it is not specify (which starts a new feature) nor clarify (which only resolves [NEEDS CLARIFICATION] markers).

  1. Resolve the feature dir specs/NNN-slug/. If it — or its spec.md — cannot be found, report a clear error and make no changes.
  2. Done-guard. If the spec.md frontmatter status: is done, make no edits: tell the author the feature is complete and to run /amby.specify for a new feature. Stop here.
  3. Otherwise continue in place (patch, never regenerate — Principle 3):
    • Add new user stories (US-#), requirements (FR-###), and success criteria (SC-###), each taking the next available number. Preserve every existing id and its text verbatim.
    • Refine existing items only where the author asked; keep their ids stable.
    • New requirements use EARS (SHALL / WHEN / WHILE / IF-THEN / WHERE); new acceptance criteria use Given/When/Then — consistent with specify.
    • Leave any story already marked status: done untouched; you may still add new stories.
  4. Set the spec.md frontmatter status: to in-progress.
  5. Design (optional). If the author is continuing the UI/design and ui.md exists, extend it in place, preserving existing sections. If ui.md does not exist, do not create it here — direct the author to run /amby.design.
  6. Keep edits minimal and token-frugal; cite the constitution by principle number where relevant.

Report what you added or changed, by id.

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. 4d ago First seen · 34 lines · 23 tokens per session scan A c12c101d6371

Subscribe to this mod's changes

amby.revise is a command published in the GitHub repository ambystechcom/AmbyKit (2 stars, last pushed 9d ago), licensed MIT. It adds 23 tokens to every session and 611 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.