Borrowing it
Nothing to install: this file belongs to design-and-deliver/claude-code-autoconfig. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/design-and-deliver/claude-code-autoconfig/main/.claude/commands/refactor.mdgit clone --depth 1 https://github.com/design-and-deliver/claude-code-autoconfigWrote 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.
[](https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/refactor)<a href="https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/refactor"><img src="https://agentmods.dev/badge/commands/design-and-deliver/claude-code-autoconfig/refactor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/refactor"><img src="https://agentmods.dev/badge/commands/design-and-deliver/claude-code-autoconfig/refactor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00015 | $0.00935 |
| Opus 5.5 | $0.00006 | $0.00374 |
| Sonnet 5.5 | $0.00003 | $0.00187 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
refactor 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactor
One session, one target: make the codebase structurally cheaper for every future session. The thresholds (~500 LOC per file, ~CC 10 per function) nominate targets — they never grade the output. Never split code just to move a number.
Argument: $ARGUMENTS — optional path to the target file. Empty → rank and pick (Step 1).
Step 0: preconditions (hard gates)
- Read CLAUDE.md and
.claude/rules/for invariants and trap lists (canonical-copy files, generated files, machine-parsed wording, append-only files). Anything named there is OFF LIMITS as a target unless the user explicitly passed it — and then flag the trap before touching it. - Run the project's test suite. Not green → STOP and report; a refactor never starts from red.
git status— uncommitted changes in the target file → stop and ask.
Step 1: pick the target (skip if a path was passed)
Rank candidate source files by payoff = churn × structural weight:
- Churn: commits touching each file in the last 90 days —
git log --since="90 days ago" --name-only --pretty=format: | sort | uniq -c | sort -rn - Size: LOC.
- Branch density: count of branch tokens (
if,else if,case,catch,&&,||, ternary?) — a cheap complexity proxy; good enough for ranking, no linter needed.
Exclude: generated files, vendored code, tests, lockfiles, and the Step-0 trap list. Show the top 5 with their numbers; target = #1.
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.
- 2mo ago First seen · 80 lines · 15 tokens per session scan A ce9ea9f7ec33
refactor is a command published in the GitHub repository design-and-deliver/claude-code-autoconfig (2 stars, last pushed 10d ago), licensed MIT. It adds 15 tokens to every session and 935 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
assemble-team
Assemble a pre-built agent team for parallel work - review, feature, debug, cross-platform, full-stack, or research.
review-code
Trigger a comprehensive code review on recent changes or specified files.
review-branch
Review an existing branch holistically before merging — blast radius, conventions, security, and spec compliance.
pr
Open a Pull Request on GitHub following team conventions. Draft by default.
review
Adversarial staff-level review of a System Design Doc. Interrogates the 10 staff questions, finds cost and failure risks, returns a verdict. Sensors and evals gate.
code-review
Review staged git changes for bugs, security issues, and style violations.