All skills & plugins / Claude Code official plugins
code-modernization
Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code, and a plan you approve, then an upgrade, a rewrite or a rebuild with independent proof that the new code behaves like the old. Includes security hardening, a one-page report, specialist agents, and an optional live progress pane (early access).
- Type
- Plugin by Anthropic
- Catalog
- Claude Code official plugins
- Source
- anthropics/claude-plugins-official/plugins/code-modernization (105 files scanned)
- Install and details
- Agent Skills Index entry
- License
- Apache-2.0 (LICENSE file)
- Signals
- Pre-approved shellHooksBundled scriptsSpawns processes
Pre-approved tools
Shell (any command). Tools listed in allowed-tools (or an agent's tools) can be used without a permission prompt while the skill is active, depending on your agent and settings.
| Kind | Tools |
|---|---|
| read/search | ReadGlobGrep |
| write/edit files | WriteEdit |
| shell, any command | Bash |
Declared in agents/scaffolder.md, agents/test-engineer.md, agents/legacy-analyst.md, agents/business-rules-extractor.md, agents/security-auditor.md, agents/version-delta-analyst.md.
Hooks
Hooks run automatically on these agent events, without you invoking the skill: PostToolUseFailure, SessionStart, Stop, StopFailure, UserPromptSubmit.
| Event | Matcher | Runs |
|---|---|---|
| UserPromptSubmit | all | sh "${CLAUDE_PLUGIN_ROOT}/scripts/telemetry.sh" command |
| Stop | all | sh "${CLAUDE_PLUGIN_ROOT}/scripts/telemetry.sh" state |
| Stop | all | sh "${CLAUDE_PLUGIN_ROOT}/scripts/telemetry.sh" run |
| SessionStart | all | sh "${CLAUDE_PLUGIN_ROOT}/scripts/telemetry.sh" health |
| PostToolUseFailure | all | sh "${CLAUDE_PLUGIN_ROOT}/scripts/telemetry.sh" failure |
| StopFailure | all | sh "${CLAUDE_PLUGIN_ROOT}/scripts/telemetry.sh" failure |
MCP servers and apps
None.
Bundled code
59 code files (JavaScript, Python, Shell, TypeScript); first 40 listed:
code-modernization/tests/logic.test.tscode-modernization/tests/hostile.test.tscode-modernization/tests/stacks.test.tscode-modernization/tests/register.test.tscode-modernization/tests/verification.test.tscode-modernization/tests/mount.test.tstests/fixtures/world.tstests/fixtures/workspace.tstests/fixtures/stacks.tstests/fixtures/inputs.tscode-modernization/scripts/make_shards.pycode-modernization/scripts/compare.pycode-modernization/scripts/render_rules.pycode-modernization/scripts/uplift_checks.pycode-modernization/scripts/trace_rules.py- and 44 more
Network calls
No HTTP or socket call pattern found in the code.
Starts other programs
14 files. First match per file:
plugins/code-modernization/scripts/tests/test_report_tools.py:614for word in ("innerHTML", "outerHTML", "insertAdjacentHTML", "document.write", "eval(", "new Function", "setTimeout(\"", "fetch(", "XMLHttpRplugins/code-modernization/scripts/tests/test_telemetry.py:476done = subprocess.run([sys.executable, "-c", code], input=json.dumps({"cwd": self.ws}), capture_output=True, text=True, timeout=20,plugins/code-modernization/scripts/tests/test_rules_tools.py:14return subprocess.run([sys.executable, os.path.join(SCRIPTS, script), *args], capture_output=True, text=True)
plugins/code-modernization/scripts/tests/test_proof_tools.py:487with um.patch("subprocess.Popen", refuse), um.patch("os.system", refuse), um.patch("os.popen", refuse):plugins/code-modernization/hooks/tests-run.ts:45const pytest = /=+\s*((?:\d+\s+\w+,?\s*)+)\s+in\s+[\d.]+s/.exec(output)
Credentials referenced
No key, token or secret environment variable found in code or MCP config.
Static scan of commit 41f619d on 2026-10-27. Signals are patterns found in the files, not a verdict: a network call can be the whole point of a skill. Read the linked lines before you decide. How the scan works.