メニュー
Count lines of code, analyze codebase size and composition, compare code between versions. Use when the user asks about lines of code, codebase size, language breakdown, or code statistics.
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。
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/asynkron/asynkron-skills --skill cloc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。
Evaluate and improve an API by inventing real, valuable tasks, attempting them through the public API, measuring the usefulness of its features and data, and turning failures into verified fixes or evidence-backed retirement proposals. Use when asked to dogfood, audit, rationalize, improve, simplify, or find value in an API; assess whether endpoints or features produce useful information; or decide what to keep, fix, combine, document, or retire.
Keep iterating on the next logical step in a project until a clear stop condition is reached. Use when the user says `/continue-loop`, asks to "keep going", "continue iterating", or wants Codex to repeatedly choose the highest-leverage next task, execute it, verify it, and then continue. Good for open-ended cleanup, refactoring, polish, debt burn-down, and project advancement where the next step should be discovered from the current repo state instead of handed over explicitly.
Find and explain churn hotspots and unstable code clusters in a git repo. Goes beyond a flat "most-edited files" list — auto-detects clusters by directory, by filename stem (foo.go + foo_test.go), and by co-change (files that change together) — then classifies each cluster (unstable / under-development / buggy / tightly-coupled / spec-shifting) and explains *why* it's a problem. Trigger whenever the user asks about churn, hotspots, unstable code, files that change a lot, refactoring candidates, technical debt hotspots, "what's a mess", "/hotmess", or any combination of folder + time window where they want insight rather than just numbers. Auto-detects code files when no extension is given.
SKILL.md を表示中
SOC 職業分類に基づく
| name | cloc |
| description | Count lines of code, analyze codebase size and composition, compare code between versions. Use when the user asks about lines of code, codebase size, language breakdown, or code statistics. |
| argument-hint | [path or git ref] |
Before running cloc, check if it is installed:
which cloc
If not found, install it:
brew install clocnpm install -g clocsudo apt install clocsudo yum install cloccloc counts blank lines, comment lines, and physical lines of source code in 200+ programming languages. It can analyze files, directories, archives (tar, zip, .whl, .ipynb), and git commits/branches.
Count a directory (default: current project):
cloc .
Count using git file list (respects .gitignore):
cloc --vcs=git
Count a specific path:
cloc $ARGUMENTS
Count by file (detailed breakdown):
cloc --by-file --vcs=git
Diff between two git refs:
cloc --git --diff <ref1> <ref2>
Exclude directories:
cloc --exclude-dir=node_modules,vendor,.git .
Use these flags for machine-readable output:
--json — JSON--yaml — YAML--csv — CSV--md — Markdown table--xml — XML| Flag | Purpose |
|---|---|
--by-file | Per-file breakdown instead of per-language |
--vcs=git | Use git to get file list (respects .gitignore) |
--git | Treat arguments as git targets (commits, branches) |
--diff <a> <b> | Show added/removed/modified lines between two sources |
--exclude-dir=<d1,d2> | Skip directories |
--exclude-lang=<l1,l2> | Skip languages |
--include-lang=<l1,l2> | Only count these languages |
--force-lang=<lang>,<ext> | Map file extension to a language |
--processes=N | Parallel processing (N cores) |
--quiet | Suppress progress output |
--vcs=git over bare . to avoid counting generated/vendored files--json when the user needs to process the output programmatically--git --diff <ref1> <ref2>--processes=N to speed things up