Add Claude no-model-invocation integration option

[wondr-wclabs]

Fixes #2654.

Summary

Adds a Claude-specific --no-model-invocation integration option so users can install Spec Kit's Claude skills as user-invocable only:

specify init my-project --integration claude --integration-options="--no-model-invocation"

The option defaults to the current behavior, so generated Claude skills still use disable-model-invocation: false unless the flag is explicitly supplied.

Rationale

The main issue in #2654 is Claude's skill-listing budget in larger monorepos. Only changing the core Claude setup() path would leave skills generated later by the bundled agent-context extension, extension commands, or preset overrides as model-invocable, which partially defeats the opt-out. This threads parsed integration options through shared skill post-processing so the same Claude flag is applied consistently to:

• core Spec Kit Claude skills generated during init/upgrade
• bundled extension skills such as speckit-agent-context-update
• extension and preset-generated SKILL.md files

The raw and parsed integration options are also mirrored into init-options.json, while integration.json remains the structured integration-state source used by install/upgrade/switch flows. That lets later skill writers read the active option without needing to know the integration-state schema directly.

Validation

• uv sync --extra test
• uv run python -m pytest tests/integrations/test_integration_claude.py -q
• uv run python -m pytest tests/test_extension_skills.py -k "no_model_invocation or skill_md_has_parseable_yaml" -q
• uv run python -m pytest tests/integrations/test_integration_subcommand.py -q
• uv run python -m pytest tests/test_extension_skills.py -q
• uv run python -m pytest tests/integrations/test_integration_copilot.py tests/integrations/test_integration_base_skills.py -q
• uv run python -m pytest tests/test_presets.py -q
• uv run specify --help
• git diff --check
• uv run python -m pytest -q (3609 passed, 45 skipped)

AI disclosure

This PR was developed with assistance from OpenAI Codex. I reviewed the implementation and validation results before submitting.

[Copilot]

Pull request overview

Adds a Claude-specific --no-model-invocation integration option and threads persisted parsed integration options through all SKILL.md post-processing paths (core init/upgrade, bundled extensions, presets, and command override rendering) so Claude skills can be installed as user-invocable only to reduce Claude’s skill-listing budget pressure (Fixes #2654).

Changes:

• Adds Claude --no-model-invocation option and applies it by setting disable-model-invocation: true in generated/rewritten Claude SKILL.md frontmatter when enabled.
• Persists raw + parsed integration options into .specify/init-options.json and ensures install/upgrade flows refresh those persisted values.
• Passes parsed_options through post_process_skill_content() across integrations and updates tests to cover init/upgrade + extension skill inheritance.

Show a summary per file

File	Description
tests/test_extension_skills.py	Adds regression test ensuring extension-generated skills inherit persisted Claude no-model-invocation option.
tests/integrations/test_integration_claude.py	Adds tests for Claude option declaration, setup behavior, init persistence, upgrade reuse, and post-processing honoring parsed options.
src/specify_cli/presets.py	Threads persisted integration_parsed_options into integration skill post-processing for preset skill registration and restoration.
src/specify_cli/integrations/vibe/init.py	Updates Vibe post-processing signature to accept and forward parsed_options.
src/specify_cli/integrations/hermes/init.py	Ensures Hermes skill generation forwards parsed_options into post-processing.
src/specify_cli/integrations/copilot/init.py	Updates Copilot post-processing signature and forwards parsed_options where applicable in skills setup.
src/specify_cli/integrations/claude/init.py	Implements --no-model-invocation option and sets/overwrites disable-model-invocation frontmatter based on parsed options.
src/specify_cli/integrations/base.py	Extends SkillsIntegration post-processing API to accept parsed_options and forwards it through skills generation.
src/specify_cli/integrations/agy/init.py	Updates Agy post-processing signature and forwards parsed_options from setup.
src/specify_cli/integrations/_migrate_commands.py	Passes raw/parsed options through to init-options update during integration upgrade.
src/specify_cli/integrations/_install_commands.py	Passes raw/parsed options through to init-options update during integration install.
src/specify_cli/integrations/_helpers.py	Extends init-options updater to optionally set/clear stored raw + parsed integration options via an explicit sentinel.
src/specify_cli/extensions.py	Threads persisted integration_parsed_options into extension skill post-processing.
src/specify_cli/commands/init.py	Persists integration raw/parsed options into init-options on init when provided.
src/specify_cli/agents.py	Applies integration post-processing (with persisted parsed options) to SKILL.md override rendering.

Copilot's findings

Tip

Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

• Files reviewed: 15/15 changed files
• Comments generated: 1

[mnriem]

As this is Claude specific it should not touch any other files than Claude integration specific files