create-change

A command that starts a spec-sync change and guides you through its questions. Spec-sync is a system for keeping written software specifications aligned with code.

In plain words
What is it for?
Use it to create a change, answer its interview questions, and identify the documents or other outputs needed next.
Why use it?
It helps turn an unclear change request into a documented plan before implementation. Human checkpoints prevent later stages from being approved too early.

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/corvidlabs/agent-3md/create-change
Clone the repo
git clone --depth 1 https://github.com/CorvidLabs/agent-3md

Made for: Claude Code.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 130 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 $0.00014 $0.00130
Opus 5 $0.00007 $0.00065
Sonnet 5 $0.00003 $0.00026
Haiku 4.5 $0.00001 $0.00013

Measured 2d ago against content hash 9af9cb3cf6a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-change 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/commands/specsync/create-change.md · 11 lines

What it actually says

  1. Run specsync change new "$ARGUMENTS" --json.
  2. Read the returned questions array and interview the user one question at a time.
  3. Record each answer with specsync change answer <id> <question-id> <answer> --json.
  4. Continue until the question list is empty, then show the selected artifacts and next action.
  5. Do not approve, implement, verify, accept, or archive until the corresponding human gate or work stage is reached.
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 · 11 lines · 14 tokens per session scan A 9af9cb3cf6a5

Subscribe to this mod's changes

create-change is a command published in the GitHub repository CorvidLabs/agent-3md (1 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 130 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.

Related

Other commands, from other repositories