Agent skill

Codemod

Codemod (JSSG, ast-grep, workflows) best practices for writing efficient, safe, and maintainable code transformations.

MITAuto-check passedDevelopment

Install Codemod

skills CLI

$ npx skills add pproenca/dot-skills --skill codemod -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install pproenca/dot-skills codemod --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/pproenca/dot-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/.experimental/codemod .claude/skills/codemod && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "codemod" agent skill from https://github.com/pproenca/dot-skills/tree/master/skills/.experimental/codemod into .claude/skills/codemod/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codemod", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/pproenca/dot-skills/tree/master/skills/.experimental/codemod

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add pproenca/dot-skills --skill codemod -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install pproenca/dot-skills codemod --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/pproenca/dot-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/.experimental/codemod .agents/skills/codemod && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "codemod" agent skill from https://github.com/pproenca/dot-skills/tree/master/skills/.experimental/codemod into .agents/skills/codemod/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codemod", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add pproenca/dot-skills --skill codemod -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install pproenca/dot-skills codemod --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/pproenca/dot-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/.experimental/codemod .cursor/skills/codemod && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "codemod" agent skill from https://github.com/pproenca/dot-skills/tree/master/skills/.experimental/codemod into .cursor/skills/codemod/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codemod", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/pproenca/dot-skills.git --path skills/.experimental/codemod

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add pproenca/dot-skills --skill codemod -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install pproenca/dot-skills codemod --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/pproenca/dot-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/.experimental/codemod .gemini/skills/codemod && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "codemod" agent skill from https://github.com/pproenca/dot-skills/tree/master/skills/.experimental/codemod into .gemini/skills/codemod/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codemod", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install pproenca/dot-skills codemod

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add pproenca/dot-skills --skill codemod -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/pproenca/dot-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/.experimental/codemod .github/skills/codemod && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "codemod" agent skill from https://github.com/pproenca/dot-skills/tree/master/skills/.experimental/codemod into .github/skills/codemod/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codemod", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add pproenca/dot-skills --skill codemod -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install pproenca/dot-skills codemod --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/pproenca/dot-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/.experimental/codemod .opencode/skills/codemod && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "codemod" agent skill from https://github.com/pproenca/dot-skills/tree/master/skills/.experimental/codemod into .opencode/skills/codemod/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codemod", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: codemod
GitHub stars: 214
Token cost: ~2k tokens
SKILL.md length: 517 words
Files: 54 (incl. references, assets)
Skills in repo: 182
Repo updated: Aug 15, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Codemod (JSSG, ast-grep, workflows) best practices for writing efficient, safe, and maintainable code transformations.

Works in 11 steps: AST Understanding (CRITICAL) → Pattern Efficiency (CRITICAL) → Parsing Strategy (CRITICAL) → …
Tasks involving codemod
SKILL.md covers When to Apply, Rule Categories by Priority, Quick Reference and How to Use, plus 1 more section
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Codemod is an agent skill from pproenca/dot-skills. Codemod (JSSG, ast-grep, workflows) best practices for writing efficient, safe, and maintainable code transformations. This skill should be used when writing, reviewing, or debugging codemods, AST transformations, or automated refactoring tools. Triggers on tasks involving codemod, ast-grep, JSSG, code transformation, or automated migration.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 56 other files, including reference files and assets (for example `AGENTS.md`, `README.md` and `assets/templates/_template.md`).

It sits in Development, covering Code migrations. The repository describes itself as: A collection of AI agent skills following the Agent Skills open format. The licence is MIT.

When your agent uses it

Tasks involving codemod
Code transformation
Automated migration

Example prompts

“/codemod”

Workflow steps

11 steps, taken from the step headings in SKILL.md.

AST Understanding (CRITICAL)
Pattern Efficiency (CRITICAL)
Parsing Strategy (CRITICAL)
Node Traversal (HIGH)
Semantic Analysis (HIGH)
Edit Operations (MEDIUM-HIGH)
Workflow Design (MEDIUM-HIGH)
Testing Strategy (MEDIUM)
State Management (MEDIUM)
Security and Capabilities (LOW-MEDIUM)
Package Structure (LOW)

What it can do on your machine

Read from SKILL.md and the folder at commit cf93c57. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Codemod loads about 2k tokens when it runs, and up to ~25k if it reads all its reference files. Until then it costs about 88 tokens; SKILL.md has 517 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~88
When it runs · the whole SKILL.md, loaded when a task matches: ~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~25k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from pproenca/dot-skills at commit cf93c57, republished under its MIT licence (© pproenca). 517 words, ~2,033 tokens.

Download SKILL.mdSave it as .claude/skills/codemod/SKILL.md (or your agent's skills folder). This skill also uses 53 other files; get the full folder from GitHub.

name: codemod
description: Codemod (JSSG, ast-grep, workflows) best practices for writing efficient, safe, and maintainable code transformations. This skill should be used when writing, reviewing, or debugging codemods, AST transformations, or automated refactoring tools. Triggers on tasks involving codemod, ast-grep, JSSG, code transformation, or automated migration.

Codemod Best Practices

Comprehensive best practices guide for Codemod (JSSG, ast-grep, workflows), designed for AI agents and LLMs. Contains 48 rules across 11 categories, prioritized by impact to guide automated refactoring and code generation.

When to Apply

Reference these guidelines when:

Writing new codemods with JSSG or ast-grep
Designing workflow configurations for migrations
Debugging pattern matching or AST traversal issues
Reviewing codemod code for performance and safety
Setting up test fixtures for transform validation

Rule Categories by Priority

Priority	Category	Impact	Prefix
1	AST Understanding	CRITICAL	`ast-`
2	Pattern Efficiency	CRITICAL	`pattern-`
3	Parsing Strategy	CRITICAL	`parse-`
4	Node Traversal	HIGH	`traverse-`
5	Semantic Analysis	HIGH	`semantic-`
6	Edit Operations	MEDIUM-HIGH	`edit-`
7	Workflow Design	MEDIUM-HIGH	`workflow-`
8	Testing Strategy	MEDIUM	`test-`
9	State Management	MEDIUM	`state-`
10	Security and Capabilities	LOW-MEDIUM	`security-`
11	Package Structure	LOW	`pkg-`

Quick Reference

1. AST Understanding (CRITICAL)

ast-explore-before-writing - Use AST Explorer before writing patterns
ast-understand-named-vs-anonymous - Understand named vs anonymous nodes
ast-use-kind-for-precision - Use kind constraint for precision
ast-field-access-for-structure - Use field access for structural queries
ast-check-null-before-access - Check null before property access

2. Pattern Efficiency (CRITICAL)

pattern-use-meta-variables - Use meta variables for flexible matching
pattern-avoid-overly-generic - Avoid overly generic patterns
pattern-combine-with-rules - Combine patterns with rule operators
pattern-use-constraints - Use constraints for reusable matching logic
pattern-use-relational-patterns - Use relational patterns for context
pattern-ensure-idempotency - Ensure patterns are idempotent

3. Parsing Strategy (CRITICAL)

parse-select-correct-parser - Select the correct parser for file type
parse-handle-embedded-languages - Handle embedded languages with parseAsync
parse-provide-pattern-context - Provide context for ambiguous patterns
parse-early-return-non-applicable - Early return for non-applicable files

4. Node Traversal (HIGH)

traverse-use-find-vs-findall - Use find() for single match, findAll() for multiple
traverse-single-pass-collection - Collect multiple patterns in single traversal
traverse-use-stopby-for-depth - Use stopBy to control traversal depth
traverse-use-siblings-efficiently - Use sibling navigation efficiently
traverse-cache-repeated-lookups - Cache repeated node lookups

5. Semantic Analysis (HIGH)

semantic-use-file-scope-first - Use file scope semantic analysis first
semantic-check-null-results - Handle null semantic analysis results
semantic-verify-file-ownership - Verify file ownership before cross-file edits
semantic-cache-cross-file-results - Cache semantic analysis results

Show full SKILL.md (205 more words)Show less

6. Edit Operations (MEDIUM-HIGH)

edit-batch-before-commit - Batch edits before committing
edit-preserve-formatting - Preserve surrounding formatting in edits
edit-handle-overlapping-ranges - Handle overlapping edit ranges
edit-use-flatmap-for-conditional - Use flatMap for conditional edits
edit-add-imports-correctly - Add imports at correct position

7. Workflow Design (MEDIUM-HIGH)

workflow-order-nodes-by-dependency - Order nodes by dependency
workflow-use-matrix-for-parallelism - Use matrix strategy for parallelism
workflow-use-manual-gates - Use manual gates for critical steps
workflow-validate-before-run - Validate workflows before running
workflow-use-conditional-steps - Use conditional steps for dynamic workflows

8. Testing Strategy (MEDIUM)

test-use-fixture-pairs - Use input/expected fixture pairs
test-cover-edge-cases - Cover edge cases in test fixtures
test-use-strictness-levels - Choose appropriate test strictness level
test-update-fixtures-intentionally - Update test fixtures intentionally
test-run-on-subset-first - Test on file subset before full run

9. State Management (MEDIUM)

state-use-for-resumability - Use state for resumable migrations
state-make-transforms-idempotent - Make transforms idempotent for safe reruns
state-log-progress-for-observability - Log progress for long-running migrations

10. Security and Capabilities (LOW-MEDIUM)

security-minimize-capabilities - Minimize requested capabilities
security-validate-external-inputs - Validate external inputs before use
security-review-before-running-third-party - Review third-party codemods before running

11. Package Structure (LOW)

pkg-use-semantic-versioning - Use semantic versioning for packages
pkg-write-descriptive-metadata - Write descriptive package metadata
pkg-organize-by-convention - Organize package by convention

How to Use

Read individual reference files for detailed explanations and code examples:

Section definitions - Category structure and impact levels
Rule template - Template for adding new rules

Full Compiled Document

For a complete guide with all rules expanded, see AGENTS.md.

Files

SKILL.md and 53 other files (references, assets) in skills/.experimental/codemod of pproenca/dot-skills.

SKILL.md
AGENTS.md
README.md
assets/templates/_template.md
metadata.json
references/_sections.md
references/ast-check-null-before-access.md
references/ast-explore-before-writing.md
references/ast-field-access-for-structure.md
references/ast-understand-named-vs-anonymous.md
references/ast-use-kind-for-precision.md
references/edit-add-imports-correctly.md
references/edit-batch-before-commit.md
references/edit-handle-overlapping-ranges.md
references/edit-preserve-formatting.md
references/edit-use-flatmap-for-conditional.md
references/parse-early-return-non-applicable.md
references/parse-handle-embedded-languages.md
… and 36 more

Open the folder on GitHubat commit cf93c57

Compare with similar skills

Codemod next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Codemod compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Codemod this skillpproenca/dot-skills	214	—	~2k	Automated safety check: Pass	MIT	1 mo ago
Migrate Core Code to Submodulestinyhumansai/openhuman	41k	—	~2.6k	Automated safety check: Pass	GPL-3.0	yesterday
Migrate Internal Package into GhostTryGhost/Ghost	55k	—	~3.8k	Automated safety check: Pass	MIT	yesterday
ast-grep Structural Searchcode-yeongyu/oh-my-openagent	70k	—	~3.3k	Automated safety check: Pass	MIT	yesterday
Deprecate R Functions and Argumentstidyverse/dplyr	5.1k	1 repos	~1.2k	Automated safety check: Pass	Custom licence	4 mo ago
Rust Path Typesopeninterpreter/openinterpreter	69k	2 repos	~605	Automated safety check: Pass	Apache-2.0	yesterday

Similar skills

Migrate Core Code to Submodules
tinyhumansai/openhuman
Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.
41k GitHub stars~2.6k tokensUpdated yesterday
DevelopmentAuto-check passed
Migrate Internal Package into Ghost
TryGhost/Ghost
Moves a package from another TryGhost repository into Ghost as an internal workspace package while keeping its Git history, with checkpoints for the steps that need an administrator.
55k GitHub stars~3.8k tokensUpdated yesterday
DevelopmentAuto-check passed
ast-grep Structural Search
code-yeongyu/oh-my-openagent
Searches and rewrites code by syntax-tree shape across 25 languages with ast-grep, for codemods, structural queries and YAML lint rules, using a Python wrapper script.
70k GitHub stars~3.3k tokensUpdated yesterday
DevelopmentAuto-check passed
Deprecate R Functions and Arguments
tidyverse/dplyr
Walks through deprecating an R function or argument in a package: lifecycle warning, silenced tests, a new snapshot test, documentation badge and NEWS entry.
5.1k GitHub starsUsed in 1 repo~1.2k tokens
DevelopmentAuto-check passed
Rust Path Types
openinterpreter/openinterpreter
Rules for choosing Rust types for filesystem paths in new Codex code, covering protocol types, internal use and model tool arguments.
69k GitHub starsUsed in 2 repos~605 tokens
DevelopmentAuto-check passed
Convert Internal Package to TypeScript
TryGhost/Ghost
Moves a legacy internal Ghost package from JavaScript and CommonJS to TypeScript and ESM in three focused commits that keep git file history intact.
55k GitHub stars~1.2k tokensUpdated yesterday
DevelopmentAuto-check passed

Questions about Codemod

What does Codemod do?

Codemod (JSSG, ast-grep, workflows) best practices for writing efficient, safe, and maintainable code transformations. Codemod is an agent skill from pproenca/dot-skills. Codemod (JSSG, ast-grep, workflows) best practices for writing efficient, safe, and maintainable code transformations.

When should I use Codemod?

Codemod fits situations like: tasks involving codemod; code transformation; automated migration.

How do I install Codemod in Claude Code?

Run `npx skills add pproenca/dot-skills --skill codemod -a claude-code`. Or copy the skill folder (skills/.experimental/codemod in pproenca/dot-skills) into .claude/skills/codemod in your project. Claude Code loads it when a task matches its description.

How do I install Codemod in Codex?

Run `npx skills add pproenca/dot-skills --skill codemod -a codex`. Or copy the skill folder (skills/.experimental/codemod in pproenca/dot-skills) into .agents/skills/codemod in your project. Codex loads it when a task matches its description.

Can I use Codemod in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add pproenca/dot-skills --skill codemod -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codemod, .gemini/skills/codemod, .github/skills/codemod and .opencode/skills/codemod in your project.

What does Codemod need to run?

SKILL.md names no scripts, command-line tools or credentials: Codemod is instructions for the agent only.

Does Codemod access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Codemod safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Codemod use?

Codemod is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Codemod use?

About 2k tokens (SKILL.md is roughly 8.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 23k tokens, read only when the agent opens those files.

What are the alternatives to Codemod?

Skills that share tags, products or a category with Codemod: Migrate Core Code to Submodules (tinyhumansai/openhuman, 41k stars), Migrate Internal Package into Ghost (TryGhost/Ghost, 55k stars), ast-grep Structural Search (code-yeongyu/oh-my-openagent, 70k stars) and Deprecate R Functions and Arguments (tidyverse/dplyr, 5.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codemod?

pproenca (a GitHub user) maintains it in pproenca/dot-skills, which has 214 GitHub stars. The repository holds 182 skills in this directory. The repository was last updated on August 15, 2026.

Source: pproenca/dot-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Codemod

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Codemod Best Practices

When to Apply

Rule Categories by Priority

Quick Reference

1. AST Understanding (CRITICAL)

2. Pattern Efficiency (CRITICAL)

3. Parsing Strategy (CRITICAL)

4. Node Traversal (HIGH)

5. Semantic Analysis (HIGH)

6. Edit Operations (MEDIUM-HIGH)

7. Workflow Design (MEDIUM-HIGH)

8. Testing Strategy (MEDIUM)

9. State Management (MEDIUM)

10. Security and Capabilities (LOW-MEDIUM)

11. Package Structure (LOW)

How to Use

Full Compiled Document

Files

Compare with similar skills

Similar skills

More from pproenca/dot-skills

Related

Questions about Codemod