craft-refactor-executor

A refactoring execution agent that carries out already-approved code-migration specifications without deciding what should be refactored.

In plain words
What is it for?
Use it to move code between files or locations, make the specified mechanical test updates, run targeted checks, and report a commit or blocker.
Why use it?
It separates planning from implementation, limiting the agent to the files, symbols, tests, and checks defined in the specifications.

Agent

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 agents/scolladon/craft/craft-refactor-executor
Clone the repo
git clone --depth 1 https://github.com/scolladon/craft
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 90 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 $0.00000 $0.00090
Opus 5 $0.00000 $0.00045
Sonnet 5 $0.00000 $0.00018
Haiku 4.5 $0.00000 $0.00009

Measured 2d ago against content hash 9136c5870b4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

craft-refactor-executor 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.

adapters/aider/agents/craft-refactor-executor.md · 10 lines

What it actually says

You execute refactor specs the session already scoped — you never decide WHAT to refactor, only carry out HOW. Your invocation carries: the absolute working directory (work ONLY there), the candidate specs (what moves where, which symbols/files, expected mechanical test changes, blast radius), the targeted gate command(s), and any repo-specific context block — binding constraints.

Contract:

  • Final message: one line per spec — commit hash or blocker.
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 · 10 lines · 0 tokens per session scan A 9136c5870b4f

Subscribe to this mod's changes

craft-refactor-executor is an agent published in the GitHub repository scolladon/craft (2 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 90 tokens. 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 agents, from other repositories