Quickstart

New to Codemod? Follow the step-by-step guide to scaffold, test, and publish your first codemod.

Command Relationships

The Codemod CLI provides different commands for different stages of development:

High-Level Commands (Production)

# Run a published package from the registry
npx codemod @org/my-package

# Run a local workflow package
npx codemod workflow run -w ./my-package/

Use for: Production codemods, multi-step workflows, parameterized transforms

Quick Testing Commands (Development)

# Test a jssg transform directly
npx codemod jssg run ./transform.ts ./src --language tsx

# Test jssg transform with fixtures
npx codemod jssg test ./transform.ts --language tsx

Use for: Rapid iteration, testing patterns, development

Package Lifecycle

# Scaffold a new package
npx codemod init

# Validate workflow
npx codemod workflow validate -w workflow.yaml

# Publish to registry
npx codemod publish

When to use what: Use codemod workflow run for orchestrated, multi-step transformations with parameters. Use codemod jssg run for quick testing of a single jssg transform during development.

CLI Command Reference

Codemod CLI is accessible using the npx codemod command. The following commands and options are available:

`codemod ai`

In an interactive terminal, bare npx codemod opens a launcher. In npm-based usage, that launcher refreshes to the latest published CLI before prompting you to create a package or run one from the registry. In non-interactive contexts, the CLI prints next steps and exits with status 1.

Manage Master Codemod Skill (MCS) lifecycle for supported harnesses. ai Install the codemod MCS skill package, configure Codemod MCP, and install the universal /codemod entrypoint where the harness supports it.

npx codemod ai [--harness <claude|goose|opencode|cursor|codex|auto>] [--project|--user] [--force] [--no-interactive] [--update-policy <manual|notify|auto-safe>] [--update-source <local|registry|URL>] [--require-signed-manifest|--allow-unsigned-manifest] [--format <logs|table|json|yaml>]

Interactive prompts are enabled by default in TTY sessions. Use --no-interactive to skip prompts and use flags/defaults directly. Along with skill files, install writes or updates a Codemod MCP server entry:

{
  "mcpServers": {
    "codemod": {
      "command": "npx",
      "args": ["codemod@latest", "mcp"]
    }
  }
}

For Opencode, install writes opencode.json using the Opencode-specific mcp schema instead of mcpServers. MCP config paths by harness and scope:

claude: ./.mcp.json (project), ~/.mcp.json (user)
goose: ./.goose/mcp.json (project), ~/.config/goose/mcp.json (user)
opencode: ./opencode.json (project), ~/.config/opencode/opencode.json (user)
cursor: ./.cursor/mcp.json (project), ~/.cursor/mcp.json (user)
codex (CLI + macOS app): ./.codex/config.toml (project), ~/.codex/config.toml (user) under [mcp_servers.codemod]

If a conflicting Codemod MCP entry already exists, re-run with --force to overwrite it. For Opencode, Codemod leaves any legacy ./.opencode/mcp.json or ~/.opencode/mcp.json file in place to avoid deleting unrelated MCP servers. ai also upserts a managed Codemod discovery section in harness discovery guides (project root for --project, home directory for --user) without duplicating entries:

claude: CLAUDE.md
goose: AGENTS.md and .goosehints
cursor: AGENTS.md
opencode: AGENTS.md
codex: AGENTS.md ai also installs /codemod where the harness has a native command or workflow file surface:
claude: ./.claude/commands/codemod.md (project), ~/.claude/commands/codemod.md (user)
goose: ~/.config/goose/recipes/codemod.yaml + ~/.config/goose/config.yaml registration (user only)
opencode: ./.opencode/commands/codemod.md (project), ~/.config/opencode/commands/codemod.md (user)
cursor: ./.cursor/commands/codemod.md (project), ~/.cursor/commands/codemod.md (user) The installed /codemod command routes by intent:
create, scaffold, or refine codemods -> codemod authoring flow
search, run, or apply existing codemods -> registry discovery and execution flow

The generated Codemod skill package includes these authored files:

SKILL.md: the main skill instructions and Codemod-specific authoring and execution defaults
agents/openai.yaml: the Codemod agent interface definition used by compatible harnesses
commands/codemod.md: the /codemod command routing rules for harnesses with a native command surface

The installed skill also points users to CLI fallbacks when MCP is unavailable or blocked. The main user-reproducible commands are:

npx codemod ai docs: list docs resources exposed through the CLI
npx codemod ai docs <resource-id>: read a specific docs resource such as codemod-cli, codemod-creation-workflow, or codemod-troubleshooting
npx codemod ai dump-ast <file> or npx codemod ai dump-ast --: inspect AST shape for a file or stdin
npx codemod ai node-types <language>: inspect tree-sitter node kinds for a language
npx codemod ai call validate_codemod_package --input '{"package_path":"."}': validate whether a codemod package still contains starter scaffold markers or other package-surface issues
npx codemod ai feedback --category <category> --message <message>: submit short anonymous platform feedback after consent is recorded

ai also wires a periodic, cooldown-protected update check trigger:

claude: hooks.SessionStart command in ./.claude/settings.json (project) or ~/.claude/settings.json (user)
cursor: hooks.afterAgentResponse command in ./.cursor/hooks.json (project) or ~/.cursor/hooks.json (user)
opencode: plugin codemod-periodic-update.js in ./.opencode/plugins/ (project) or ~/.config/opencode/plugins/ (user), listening to session.idle
goose: managed codemod-periodic-update block in ./.goosehints (project) or ~/.config/goose/.goosehints (user) as fallback guidance
codex: notify = ["sh", "<runner>"] in ./.codex/config.toml (project) or ~/.codex/config.toml (user) Managed update policy is install-flag driven and shared by install-time reconciliation and periodic checks:
--update-policy <manual|notify|auto-safe> (default: auto-safe)
--update-source <local|registry|URL> (default: registry)
--require-signed-manifest or --allow-unsigned-manifest (optional override) --update-source only accepts local, registry, or an absolute http(s) URL (legacy registry:/url: aliases are rejected). Periodic runs enforce signed manifest verification via --require-signed-manifest in the generated runner command. After install, restart or reload your harness session so newly installed skills and command entrypoints are picked up.

ai feedback Submit short anonymous platform feedback for Codemod AI, MCP, JSSG, workflows, docs, CLI, registry, or related surfaces. The command records anonymous feedback consent in the user-wide Codemod config, including the timestamp at which this OS user allowed feedback submission.

npx codemod ai feedback --category <category> --message <message>

Recommended categories are jssg, workflow, ai-docs, mcp, cli, registry, package-validation, and other. Examples:

npx codemod ai feedback --category jssg --message "I wish JSSG had clearer examples for multi-file transforms."
npx codemod ai feedback --category ai-docs --message "The docs resource for runtime capabilities should explain which Node APIs are unavailable."

Feedback is anonymous. Do not include source code, secrets, auth tokens, private repository paths, user identity, or long transcripts in the message. ai update Run managed update reconciliation/apply through CLI (same policy engine used by periodic hooks).

npx codemod ai update [--harness <claude|goose|opencode|cursor|codex|auto>] [--project|--user] [--force] [--no-interactive] [--update-policy <manual|notify|auto-safe>] [--update-source <local|registry|URL>] [--require-signed-manifest|--allow-unsigned-manifest] [--format <logs|table|json|yaml>]

If managed install state is missing, ai update automatically falls back to an install flow and then applies update reconciliation. ai performs internal skill validation checks during install flow. ai list List installed Codemod skills for a harness.

npx codemod ai list [--harness <claude|goose|opencode|cursor|codex|auto>] [--format <logs|table|json|yaml>]

Use this command to inspect which Codemod-managed skills are already installed for a given harness before running codemod ai again or troubleshooting harness setup. ai dump-ast Dump AST nodes for a source file or stdin using the same parser surface exposed through Codemod MCP.

npx codemod ai dump-ast [FILE] [--language <language>] [--json]

Omit FILE or pass - to read from stdin.
If you do not pass --language, the CLI infers it from the file extension when possible and otherwise defaults to tsx for stdin.

# Parse a file and print AST text
npx codemod ai dump-ast ./src/component.tsx

# Parse stdin as TypeScript and emit JSON
cat ./src/index.ts | npx codemod ai dump-ast - --language typescript --json

ai node-types Print tree-sitter node types for a supported language.

npx codemod ai node-types <language> [--json]

npx codemod ai node-types tsx
npx codemod ai node-types python --json

ai docs List, read, or search Codemod AI documentation resources from the CLI.

npx codemod ai docs [query...] [--json]

Run without a query to list available docs-backed resources.
Pass a resource name or URI to read it.
Pass a search phrase to search across available resources.

# List available docs resources
npx codemod ai docs

# Read one resource by name
npx codemod ai docs codemod-cli-instructions

# Search across docs-backed resources
npx codemod ai docs semantic analysis

ai tools and ai tool Inspect MCP-equivalent tools exposed by the CLI.

npx codemod ai tools [--json]
npx codemod ai tool <name> [--json]

ai tools lists available tool names and descriptions.
ai tool <name> prints metadata and the JSON input schema for a single tool.

ai call Call an MCP-equivalent tool directly from the CLI with JSON input.

npx codemod ai call <name> [--input <JSON|@path|- >]

Omit --input to pass an empty object ({}).
Use --input @request.json to load input from a file.
Use --input - to read JSON input from stdin.

npx codemod ai call dump_ast --input '{"language":"tsx","source":"const x = 1;"}'

ai resources and ai resource Inspect and read MCP-equivalent resources exposed by the CLI.

npx codemod ai resources [--json]
npx codemod ai resource <uri-or-name> [--json]

ai resources lists the available resource names and URIs.
ai resource reads one resource by URI or resource name.

Package skill install (prompted from package run)

Install a package skill from registry metadata into harness skill paths. The installer copies the authored skill directory recursively from the package (agents/skill/<skill-name>/), including any additional files you add (for example extra .md references). This flow also updates managed Codemod discovery hints in harness discovery guides (CLAUDE.md for Claude, AGENTS.md and .goosehints for Goose, AGENTS.md for Cursor/OpenCode/Codex) without duplication, then prompts you to restart/reload the harness session.

npx codemod <package-id>

In interactive TTY sessions, npx codemod <package-id> prompts for harness/scope/overwrite when installable skill behavior is available.

Behavior-aware package runtime:

Workflow-only package: npx codemod <package-id> runs the workflow behavior.
Skill-only package: npx codemod <package-id> does not run a no-op workflow. It returns install guidance and, in interactive terminals, can prompt to install the skill.
Workflow + skill package: npx codemod <package-id> runs workflow behavior and can optionally prompt to install skill behavior after run completion.
Multi-workflow package: when the package’s codemod.yaml declares multiple workflows under workflows:, the default workflow runs unless you pass --workflow <name>. In an interactive terminal with no flag, the CLI shows a picker.

AI-native error codes

Code	Exit	Meaning
`E_SKILL_PACKAGE_NOT_FOUND`	`27`	Unknown package id / unresolved package version
`E_SKILL_PACKAGE_INSTALL_FAILED`	`28`	Registry resolution, metadata parse, or install write failure

Example machine-readable failure (--format json):

{
  "ok": false,
  "code": "E_SKILL_PACKAGE_NOT_FOUND",
  "exit_code": 27,
  "message": "Unknown skill package id: jest-to-vitestx",
  "hint": "Run `codemod search <migration> --format json` to locate a valid package id."
}

`codemod workflow`

Manage and execute Codemod packages. A Codemod package is a directory containing workflow.yaml and transformation scripts. Workflows orchestrate multiple steps using different engines (jssg, YAML ast-grep, shell commands, AI, etc.). When to use:

✅ Production codemods with multiple steps
✅ Parameterized transformations
✅ Multi-repo orchestration
✅ State management and resumption

Learn more: Workflow Reference workflow run Run a complete Codemod package.

Use npx codemod workflow run -w <path> for local Codemod packages and directories
Use npx codemod <package-name> to run packages directly from the Codemod Registry

npx codemod workflow run -w <workflow.yaml|directory>

npx codemod <package-name>

string

required

Path to workflow file or directory.

string

Target directory to run the workflow on.

# Specify a target directory
npx codemod workflow run -w ./my-codemod -t /abs/path/to/repo

# Specify a target directory
npx codemod @codemod/my-test-pkg -t /abs/path/to/repo

string

Pass key=value pairs to your workflow. Parameters are exposed to jssg transforms via options.params.

# Single parameter:
npx codemod workflow run -w workflow.yaml --param format=cjs

# Multiple parameters:
npx codemod workflow run -w workflow.yaml --param format=cjs --param strict=true

boolean

In non-interactive runs, execute install-skill workflow steps instead of skipping them by default.

npx codemod workflow run -w workflow.yaml --no-interactive --install-skill
npx codemod <package-name> --no-interactive --install-skill

string

When the package directory’s codemod.yaml declares multiple workflows under workflows:, pick which variant to run.Without this flag, the entry marked default: true runs (or the first entry if none is flagged). When stdin/stdout are interactive and no flag is given, the CLI shows a picker.

# Run a named workflow defined in the package's codemod.yaml
npx codemod workflow run -w ./my-codemod --workflow-name sharded

Errors out if the name doesn’t match any declared workflow, or if the source path is a workflow file (rather than a package directory) — in that case the file IS the workflow.

string

Write provider-reported nested LLM usage for the current package run to a JSON file.This output is only populated for LLM requests made by nested codemods during npx codemod <package-name> or other package-run flows. The file contains aggregated request counts by provider, model, outcome, and token-usage bucket, and it does not include prompts, API keys, or other request payload data.

# Capture nested LLM usage while running a registry package
npx codemod @org/my-package --llm-usage-output ./artifacts/llm-usage.json

# Capture nested LLM usage for a local package run
npx codemod workflow run -w ./my-codemod --llm-usage-output ./artifacts/llm-usage.json

The CLI creates parent directories as needed and overwrites the file with the current run’s data.

workflow resume Resume a paused workflow.

npx codemod workflow resume -i <ID> [-t <TASK>] [--trigger-all]

string

required

Workflow run ID.

string

Task ID to trigger (can be specified multiple times).

boolean

Trigger all awaiting tasks.

boolean

In non-interactive resume runs, execute pending install-skill workflow steps instead of skipping them by default.

npx codemod workflow resume -w workflow.yaml -i <ID> --trigger-all --no-interactive --install-skill

workflow validate Validate a workflow file.

npx codemod workflow validate -w <workflow.yaml>

workflow validate is capability-aware for codemod packages:

Workflow-only package: validates workflow behavior.
Skill-only package: validates workflow install-skill behavior plus authored skill layout (agents/skill/<skill-name>/...).
Workflow + skill package: validates both executable workflow and authored skill behavior.

string

required

Path to workflow file or codemod package directory.

Check	Ensures
Schema validation	YAML matches the workflow spec
Unique IDs	Node & template IDs are unique
Dependency validation	Every `depends_on` exists
Cyclic dependency detection	DAG has no cycles
Template references	All `template:` IDs exist
Matrix validation	`from_state` matches schema
State schema validation	`state.schema` is valid
Variable syntax	`${{…}}` uses `params`, `env`, `state`

Why validate?Validation catches issues before execution, saving time and preventing runtime errors.

Validation vs. Logical Correctness

For workflow behavior, workflow validate ensures your YAML is syntactically correct and follows the schema, but it cannot verify:

Logical correctness: Whether your workflow does what you intend
Runtime behavior: How your workflow behaves with real data
Dependencies: Whether external files/scripts exist
State consistency: Whether state updates are logically sound

workflow status Show workflow run status.

npx codemod workflow status -i <ID>

string

required

Workflow run ID.

workflow list List workflow runs.

npx codemod workflow list [-l <LIMIT>]

number

Number of workflow runs to show. (default: 10)

workflow cancel Cancel a workflow run.

npx codemod workflow cancel -i <ID>

string

required

Workflow run ID.

`codemod jssg`

Run jssg (JS ast-grep) transforms directly without a workflow. jssg is the primary transformation engine for Codemod. These commands let you test jssg transforms quickly during development. When to use:

✅ Quick testing of a single transform
✅ Iterating on pattern matching
✅ Development and debugging

When NOT to use:

❌ Multi-step transformations → use codemod workflow
❌ Parameterized transforms → use codemod workflow with --param
❌ Production deployments → use codemod workflow for orchestration

For production, embed your jssg transform in a workflow using a js-ast-grep step. See Workflow Reference: JSSG Step.

Learn more: jssg documentation

Write your codemod

Create a JS/TS file that exports your codemod logic.

Run your codemod

npx codemod jssg run my-codemod.js ./src --language javascript

Test your codemod

Organize your tests as follows:

tests

simple-transform

input.js

expected.js

multi-file-case

input

file1.js

file2.js

expected

file1.js

file2.js

Use the input/ + expected/ layout when the codemod creates or deletes files. The runner compares the whole directory snapshot but still reports results per file.Then run:

npx codemod jssg test my-codemod.js --language javascript

jssg run Run a JS ast-grep (jssg) codemod.

npx codemod jssg run <codemod_file> <target_directory> [options]

string

required

Path to the JS ast-grep (jssg) codemod file (JS/TS).

string

required

Directory to apply the codemod to.

string

required

Target language (e.g., javascript, typescript, python, java, cpp, php, kotlin, json, yaml, xml, toml, etc.).

string

Comma-separated list of file extensions to process.

boolean

Do not respect .gitignore files.

boolean

Include hidden files and directories in the scan.

number

Maximum number of concurrent threads to use.

boolean

Perform a dry-run to see the changes without applying them.

jssg test Test a JS ast-grep(jssg) codemod using before/after fixtures. Supports both single-file input.*/expected.* cases and directory snapshot fixtures using input/ + expected/.

npx codemod jssg test <codemod_file> [options]

string

required

Path to the JS ast-grep (jssg) codemod file, which is a JS/TS file.

string

required

Target language (e.g., javascript, typescript, python, java, cpp, php, kotlin, json, yaml, xml, toml, etc.).

string

The parent directory containing your test case subdirectories (default: "tests"). Do not pass a specific test case subdirectory — use --filter instead.

string

A pattern to run only tests whose names match the filter. Single-file fixtures use the test case directory name. Directory snapshot fixtures are still reported per file, using names like <fixture>_<relative-path>.

string

The output format for test results. Can be console, json, or terse.

boolean

Show detailed output, including diffs for failed tests.

number

The number of context lines to show in diffs (default: 3).

boolean

Ignore whitespace differences when comparing test outputs (only applies to strict mode).

string

Comparison strictness level (default: strict):

strict - Exact string equality
cst - Compare Concrete Syntax Trees (includes all tokens, preserves ordering)
ast - Compare Abstract Syntax Trees (ignores formatting, preserves ordering)
loose - Loose AST comparison (ignores formatting and ordering of unordered nodes like object properties, imports)

Supported languages: JavaScript, TypeScript, Python, Go, Rust, JSON.

number

Test timeout in seconds (default: 30).

number

Maximum number of concurrent threads to use for running tests.

boolean

Run tests sequentially instead of in parallel.

boolean

Stop the test run on the first failure.

boolean

Create or update the expected files with the output of the codemod. For directory snapshot fixtures, this also creates missing expected files and removes stale ones. (-u is a shorthand for --update-snapshots)

string

A comma-separated list of test patterns that are expected to fail.

boolean

Enable watch mode to automatically re-run tests when files change.

When should I define a workflow instead?

When you need to chain multiple codemods or scripts.
When you want manual review, approval steps, or CI/CD integration.
When you want to use engines other than ast-grep (e.g., jscodeshift, YAML, or custom scripts).

Why ast-grep?

ast-grep is extremely fast and robust for syntax-aware code transformations. We made it first-class in the CLI for the most common use case, but you can still use any engine via workflows.jssg replicates the ast-grep NAPI, but with a few key differences:

It’s built into the CLI, so you can run it directly without needing to install it separately.
It’s built for speed and simplicity, making ast-grep codemods a first-class experience.

`codemod init`

Initialize a new Codemod package project.

npx codemod init [PATH] [options]

In interactive mode, codemod init prompts you to choose between a jssg codemod, multi-step workflow, or agent skill codemod. If you select a workflow, you can optionally scaffold an agent skill. You’ll also be prompted to create a GitHub Actions publishing workflow. This generates .github/workflows/publish.yml:

Single codemod repo: Triggers on v* tags (e.g., v1.0.0)
Monorepo: Triggers on *@v* tags (e.g., my-codemod@v1.0.0) and extracts the codemod name

Both workflows use trusted publishers with OIDC for secure, passwordless publishing. See the publishing guide for detailed workflow examples.

string

Project directory name.

string

Project name (defaults to directory name).Required in --no-interactive mode when the project name cannot be derived from [PATH] (for example, when [PATH] is ., .., or another path without a final directory component).

string

Workflow project type: ast-grep-js or hybrid. Mutually exclusive with --skill.Required in --no-interactive mode for workflow packages.

More package types (advanced)

shell: Shell script-based codemods
ast-grep-yaml: YAML-based ast-grep codemods

boolean

Scaffold a skill-only package with a workflow-first template (workflow.yaml contains install-skill) and authored files under agents/skill/<skill-name>/.The generated SKILL.md uses the authored package skill markers:

codemod-compatibility: skill-package-v1
codemod-skill-version: 0.1.0

Mutually exclusive with --with-skill and --project-type.

boolean

Scaffold a workflow + skill package. This keeps executable workflow files, appends an install-skill node, and creates authored skill files under agents/skill/<skill-name>/.The generated authored skill uses skill-package-v1, not the built-in mcs-v1 core skill marker.Mutually exclusive with --skill.

string

Package manager.Required in --no-interactive mode for ast-grep-js, hybrid, and --workspace.

string

Target language.Required in --no-interactive mode.

string

Project description.Required in --no-interactive mode.

string

Author name and email.Required in --no-interactive mode.

string

License.Required in --no-interactive mode.

string

Git repository URL stored as repository in codemod.yaml.

boolean

Make package private.

boolean

Overwrite existing files.

boolean

Use defaults without prompts. In this mode, pass the values that would normally come from prompts.

npx codemod login [--api-key <API_KEY>] [--registry <REGISTRY>] [--scope <SCOPE>]

string

Authenticate using an API key. Skips the browser login & is ideal for CI.

string

Registry URL.

string

Organization or user scope for publishing.

Need a key? Generate one in the Codemod app here ->.

`codemod logout`

Logout from a registry.

npx codemod logout [--registry <REGISTRY>] [--all]

string

Registry URL to logout from.

boolean

Logout from all registries.

`codemod whoami`

Show current authentication status.

npx codemod whoami [--registry <REGISTRY>] [--detailed]

string

Registry URL to check.

boolean

Show detailed information including token scopes.

`codemod publish`

Publish a Codemod package to a registry.

npx codemod publish [PATH]

string

Path to codemod directory (defaults to current directory).

Package metadata (name, version, access level, etc.) is read from codemod.yaml. See Package Structure for configuration options.

Publishing Guide

Learn about all publishing methods including API keys, trusted publishers (OIDC), and CI/CD setup.

`codemod unpublish`

Remove a package or selected version from the registry.

npx codemod unpublish <PACKAGE> [options]

string

required

Package name (e.g., @org/my-codemod or my-codemod).

string

Specific semver to unpublish. Requires confirmation.

boolean

Unpublish all versions (irreversible). Confirmation required.

string

Target registry URL.

boolean

Show what would be removed without actually unpublishing.

The CLI always prompts for confirmation when --version or --force is used. This interactive step cannot be bypassed programmatically.

Examples

# Preview removal of a single version
npx codemod unpublish my-codemod --version 0.1.0 --dry-run

# Remove a single version (will prompt)
npx codemod unpublish my-codemod --version 0.1.0

# Remove all versions (will prompt)
npx codemod unpublish my-codemod --force

# Unpublish from a custom registry
npx codemod unpublish my-codemod --force --registry https://registry.example.com

`codemod search`

Search for packages in the registry.

npx codemod search [OPTIONS] [QUERY]

string

Search query

string

Filter by programming language

string

Filter by framework

string

Filter by category

number

Number of results to return (default: 20)

number

Pagination offset (default: 0)

string

Filter by organization scope

string

Registry URL

string

Output format (default: table). Possible values: table, json, yaml

Examples

Search for codemods related to React:

npx codemod search react

Filter by language and category:

npx codemod search --language typescript --category migration

Get results in JSON format:

npx codemod search --format json next

`codemod cache`

Manage the local package cache for Codemod packages. cache info Show cache information and statistics.

npx codemod cache info

cache list List cached packages.

npx codemod cache list [--detailed]

boolean

Show package details.

cache clear Clear cache for a specific package, or all packages.

npx codemod cache clear [PACKAGE] [--all]

string

Package name (e.g., @org/package or package).

boolean

Clear all cached packages.

cache prune Prune old or unused cache entries.

npx codemod cache prune [--max-age <MAX_AGE>] [--dry-run]

number

Maximum age in days to keep (default: 30).

boolean

Dry run - show what would be removed.

First steps

Community

Enterprise

Other Resources

Codemod CLI

Quickstart

Command Relationships

High-Level Commands (Production)

Quick Testing Commands (Development)

Package Lifecycle

CLI Command Reference

`codemod ai`

Package skill install (prompted from package run)

`codemod workflow`

`codemod jssg`

`codemod init`

`codemod logout`

`codemod whoami`

`codemod publish`

Publishing Guide

`codemod unpublish`

`codemod search`

`codemod cache`

Quickstart

​Command Relationships

​High-Level Commands (Production)

​Quick Testing Commands (Development)

​Package Lifecycle

​CLI Command Reference

​codemod ai

​Package skill install (prompted from package run)

​codemod workflow

​codemod jssg

​codemod init

​codemod login

​codemod logout

​codemod whoami

​codemod publish

Publishing Guide

​codemod unpublish

​codemod search

​codemod cache

Command Relationships

High-Level Commands (Production)

Quick Testing Commands (Development)

Package Lifecycle

CLI Command Reference

`codemod ai`

Package skill install (prompted from package run)

`codemod workflow`

`codemod jssg`

`codemod init`

`codemod login`

`codemod logout`

`codemod whoami`

`codemod publish`

`codemod unpublish`

`codemod search`

`codemod cache`