본문으로 건너뛰기
cccskills
무료GitHub에 공개

codemod-runner

Execute large-scale automated code transformations safely and idempotently. Use when renaming symbols across a codebase, migrating API call-sites, enforcing new patterns at scale, or applying structural edits to many files at once. Triggers on: 'codemod', 'mass rename', 'migrate all usages', 'transform codebase', 'apply pattern at scale', AST-based refactoring, or any task requiring consistent edits across 10 or more files.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

연동 도구Facebook
설치 방법 보기

포함된 파일(1)

  • SKILL.md5.6 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Codemod Runner

Apply automated code transformations at scale using the right AST tool for the job — with scope assessment, batch execution, and idempotency verification before committing.


Tool Selection

flowchart TD
    Start([Codemod task received]) --> Q1{Language?}
    Q1 -->|Python| Q2{Transformation type?}
    Q1 -->|JavaScript / TypeScript| Q3{Needs full type info?}
    Q1 -->|Multi-language or<br>language-agnostic| Comby["comby<br>Structural search-replace<br>Works on any language<br>Pattern: comby 'old' 'new' .py"]
    Q2 -->|Rename, rewrite,<br>API migration| LibCST["LibCST<br>Preserves formatting<br>Python CST with type safety<br>pip install libcst"]
    Q2 -->|Lightweight search-replace<br>or regex-like patterns| Comby
    Q3 -->|Yes — needs type resolution,<br>cross-file inference| TSMorph["ts-morph<br>Full TypeScript compiler API<br>npx ts-morph-cli or use API<br>Best for typed refactors"]
    Q3 -->|No — structural only| Q4{Ecosystem preference?}
    Q4 -->|AST patterns preferred| AstGrep["ast-grep<br>Fast structural search<br>npm install -g @ast-grep/cli<br>sg run -p 'pattern' -r 'rewrite'"]
    Q4 -->|Codemod ecosystem,<br>existing transforms| JSCodeshift["jscodeshift<br>Facebook codemod runner<br>npx jscodeshift -t transform.js src/"]
    Comby --> Scope
    LibCST --> Scope
    TSMorph --> Scope
    AstGrep --> Scope
    JSCodeshift --> Scope
    Scope([Proceed to scope assessment])

Phase 1 — Scope Assessment (run before any transformation)

Assess impact size before touching files:

# Count affected files
rg -l 'old-pattern' | wc -l

# Preview first 25 affected files (saves to batch list)
rg -l 'old-pattern' | head -25 > batch.list
cat batch.list

# Count total occurrences (not just files)
rg -c 'old-pattern' | awk -F: '{sum+=$2} END {print sum}'

If the file count exceeds 50, process in batches using batch.list:

# Build per-batch lists of 25 files each
rg -l 'old-pattern' | split -l 25 - batch-
ls batch-*  # batch-aa, batch-ab, ...

Phase 2 — Batch Execution

Run the codemod against one batch at a time. Replace TOOL_CMD with the selected tool:

# ast-grep example
sg run -p 'old_fn($A)' -r 'new_fn($A)' --lang python $(cat batch-aa)

# comby example
comby 'old_fn(:[args])' 'new_fn(:[args])' -f .py $(cat batch-aa)

# jscodeshift example
npx jscodeshift -t transform.js $(cat batch-aa)

# LibCST — use a script, pass files as args
uv run codemod_script.py $(cat batch-aa)

# ts-morph — use a script targeting the batch
npx ts-node transform.ts --files $(cat batch-aa)

Phase 3 — Per-Batch Idempotency Check

After each batch completes, verify the transformation is idempotent (running it twice produces zero diff):

# Run the transformation a second time on the same batch
TOOL_CMD $(cat batch-aa)

# Confirm no further changes
git diff --stat
# Expected output: (empty — no changes)

If git diff shows changes after the second run, the transformation is not idempotent. Investigate the transform logic before proceeding to the next batch.


Phase 4 — Verification Trend

After each batch, measure progress toward zero remaining occurrences:

# Before starting:  rg 'old-pattern' | wc -l  → baseline count N
# After batch 1:    rg 'old-pattern' | wc -l  → should decrease
# After all batches: rg 'old-pattern' | wc -l  → 0

# One-liner to track trend across iterations
echo "Remaining: $(rg 'old-pattern' | wc -l)"

The count MUST decrease monotonically after each batch. If it does not decrease, the transform did not apply — investigate before continuing.

Final state: rg 'old-pattern' | wc -l returns 0.


Phase 5 — Commit

Once all batches pass idempotency and the verification count reaches 0:

git add -p   # or specific files
git commit -m "codemod: migrate old-pattern → new-pattern"

Commit after all batches complete and verification passes — not per-batch.


Tool Quick Reference

SOURCE: Tool official documentation — comby (comby.dev, accessed 2026-05-22), ast-grep (ast-grep.github.io, accessed 2026-05-22), jscodeshift (github.com/facebook/jscodeshift, accessed 2026-05-22), ts-morph (ts-morph.com, accessed 2026-05-22), LibCST (libcst.readthedocs.io, accessed 2026-05-22).

ToolInstallStrengthsAvoid when
combybrew install comby or binaryLanguage-agnostic, structuralNeed type information
ast-grepnpm i -g @ast-grep/cliFast, multi-language AST patternsComplex rewrites needing APIs
jscodeshiftnpm i -g jscodeshiftRich JS/TS ecosystem, existing codemodsPython or non-JS targets
ts-morphnpm i ts-morphFull TypeScript type resolutionNo TypeScript in project
LibCSTpip install libcstFormat-preserving Python CSTJS/TS or multi-language

Large-Scale Codemod Swarm Pattern

For codebases with thousands of files, coordinate parallel workers across file batches using the /swarm-patterns skill (Pattern 6). Each worker owns one batch file, runs the codemod + idempotency check, and reports its completion count to the team lead before the final commit.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Add automated documentation updater to any Claude skill. Creates a Python sync script that downloads upstream docs, processes markdown for AI consumption, and maintains local cache with configurable refresh. Collects template variables, then delegates implementation through 5-phase workflow. Use when adding auto-updating reference documentation to plugins or skills.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Jamie-BitFlight/claude_skills672026년 10월 18일 업데이트

SAM-style feature initiation workflow — discovery through codebase analysis, architecture spec, task decomposition, validation, and context manifest. Use when a user asks to add a feature, plan a feature, or convert an idea into an executable SAM plan.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Jamie-BitFlight/claude_skills672026년 10월 18일 업데이트

Browser automation for AI agents using the agent-browser CLI and Playwright. Use when navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, logging into sites, or automating any browser task. Triggers on "open a website", "fill out a form", "click a button", "scrape data", "test this web app", "automate browser actions", or any programmatic web interaction request.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Jamie-BitFlight/claude_skills672026년 10월 18일 업데이트

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Jamie-BitFlight/claude_skills672026년 10월 18일 업데이트

Runs the description-drift experiment — spawns all Claude Code agents simultaneously to collect self-reported capabilities, then compares them against static frontmatter descriptions to reveal how reliable orchestrator routing based on descriptions actually is. Use when measuring description drift across the agent fleet, re-running the capability collection experiment, analyzing a specific agent's self-reported capabilities, or auditing whether frontmatter descriptions accurately reflect agent behavior.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Jamie-BitFlight/claude_skills672026년 10월 18일 업데이트

Create or adapt Claude Code agent definitions. Use when creating an agent, changing subagent configuration, selecting agent scope, or designing a specialized delegation role.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Jamie-BitFlight/claude_skills672026년 10월 18일 업데이트

Jamie-BitFlight의 스킬 모두 보기

이 스킬의 문제 신고