メニュー
Run Claude programmatically against collections of files in the codebase. Use for batch analysis: scrubbing sensitive data, auditing style violations, security reviews.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
SOC 職業分類に基づく
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/imbue-ai/sculptor --skill batch-claude-runnerコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SKILL.md を表示中
Build or modify a Sculptor extension — a runtime ESM module loaded into the Sculptor UI. Use when asked to write an extension (or "plugin") for Sculptor, add a panel, overlay, workspace widget, home view, or settings UI to Sculptor, or to iterate on an extension with `sculpt extension`. Works from any repo; this file is a self-contained reference (the Sculptor source code is optional).
Cut a new Sculptor release candidate from main: run `just cut-release` (which creates the release/sculptor-vX.Y.0 branch at X.Y.0rc1, pushes the tag that triggers the RC build, and opens a PR bumping main to the next .dev0), then land the version-bump PR and babysit the RC build up to its manual approval gate. Handles the colocated jj + git working-copy setup and the CI flake/outage/zombie recovery playbook. Stops AT the approval gate — never approves it for you. Use when asked to "cut a release", "cut an RC", or start a new Sculptor release.
Promote a QA'd Sculptor release candidate to a full production release: verify the RC build is green and has been QA'd, then from the release branch run `just promote-release` (which strips the rcN suffix, commits X.Y.0, and pushes the sculptor-vX.Y.0 tag that triggers the production build) and babysit that build up to its manual approval gate. Handles the colocated jj + git working copy and the CI flake/outage/zombie recovery playbook. Stops AT the approval gate — never approves it for you. Use when asked to "promote a release", "ship the release", or turn an RC into the real release.
| name | batch-claude-runner |
| disable-model-invocation | true |
| description | Run Claude programmatically against collections of files in the codebase. Use for batch analysis: scrubbing sensitive data, auditing style violations, security reviews. |
Runs Claude against batches of files, collecting structured findings into a summary report.
# Basic usage
python .claude/skills/batch-claude-runner/scripts/batch_claude_runner.py \
--pattern "**/*.py" \
--prompt "Check for hardcoded credentials or API keys."
# See all options
python .claude/skills/batch-claude-runner/scripts/batch_claude_runner.py --help
--pattern / -p: Glob pattern for files (required, repeatable)--exclude / -e: Exclude pattern (repeatable)--prompt: Analysis prompt--batch-size / -b: Files per batch (default: 10)--max-batches / -m: Limit batches (for testing)--dry-run: Preview files without running--output json: Machine-readable output--json-schema--dry-run first to verify file selection