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.
npx agentmods add commands/evan043/claude-cli-advanced-starter-pack/refactor-check.templategit clone --depth 1 https://github.com/evan043/claude-cli-advanced-starter-packWrote 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/evan043/claude-cli-advanced-starter-pack/refactor-check.template)<a href="https://agentmods.dev/commands/evan043/claude-cli-advanced-starter-pack/refactor-check.template"><img src="https://agentmods.dev/badge/commands/evan043/claude-cli-advanced-starter-pack/refactor-check.template.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00682 |
| Opus 5 | $0.00000 | $0.00341 |
| Sonnet 5 | $0.00000 | $0.00136 |
| Haiku 4.5 | $0.00000 | $0.00068 |
Grade A, and why
refactor-check.template 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 5d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Runtime Compatibility
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows:
AskUserQuestion=> ask the user directly in chat.WebSearch/WebFetch=> use available web tools (search_query,open,find) and cite links.Read/Write=> use shell/filesystem tools in this workspace.- Claude-only MCP calls (for example Playwright MCP names) => use available equivalents or clearly state fallback.
- Keep intent and output format identical; only adapt execution mechanics.
description: Fast pre-commit quality gate - lint, type-check, test affected files
Refactor Check
Quick quality validation before committing changes. Runs essential checks without full test suite.
Checks Performed
- Linting - ESLint/Pylint for code style issues
- Type Checking - TypeScript/MyPy type validation
- Affected Tests - Run tests for changed files only
- Import Validation - Verify imports resolve correctly
Usage
Run before committing to catch issues early:
/refactor-check
Implementation
When invoked, execute these steps:
Step 1: Detect Changed Files
git diff --name-only HEAD~1..HEAD
# OR for staged changes:
git diff --cached --name-only
Step 2: Run Linting (Affected Files Only)
JavaScript/TypeScript:
npx eslint <changed-files>
Python:
pylint <changed-files>
# OR
ruff check <changed-files>
Step 3: Type Checking
TypeScript:
npx tsc --noEmit
Python:
mypy <changed-files>
Step 4: Run Affected Tests
JavaScript/TypeScript:
npx jest --findRelatedTests <changed-files>
# OR
npx vitest --run --reporter=verbose <changed-files>
Python:
pytest <changed-files> --collect-only -q
Output Format
Refactor Check Results
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Files Changed: 5
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
✅ Linting: Passed (0 errors, 2 warnings)
✅ Type Check: Passed
✅ Tests: 3 passed, 0 failed
⚠️ Imports: 1 unused import detected
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Overall: PASS (ready to commit)
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.
- 5d ago First seen · 123 lines · 0 tokens per session scan A 5df582424db0
refactor-check.template is a command published in the GitHub repository evan043/claude-cli-advanced-starter-pack (61 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 682 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 2026-08-30.
Other commands, from other repositories
block-no-verify
Set up PreToolUse hook to block --no-verify and other git bypass flags in Claude Code projects.
changelog
Generate a structured changelog from recent git commits, categorized by change type.
commit-push-pr
머지 전 /sync-docs 문서 동기화 의무 게이트 → 검증 → 커밋 & PR & 머지 + MCP 알림 (v7).
setup-git
/setup-git is per-repo platform secret setup — most importantly SYNCPAT, the fine-grained PAT that allows the issue-sync workflow to author issues as the maintainer instead of as github-actions[bot]. Without SYNCPAT, every synced issue carries authorassociation: NONE and the t2449 worker-briefed auto-merge gate…
quick-commit
간단한 수정용 빠른 커밋 (v6).
commit
Creates commits with Conventional Commits format (feat/fix/docs/refactor/test/chore), automatic scope detection, co-author attribution, and pre-commit hook compliance. Validates staged changes, generates descriptive messages focusing on the 'why', and prevents secrets or generated-only files from being committed.…