code-agnostic 0.3.5__tar.gz → 0.3.8__tar.gz

{code_agnostic-0.3.5 → code_agnostic-0.3.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code-agnostic
-Version: 0.3.5
+Version: 0.3.8
 Summary: Centralized hub for LLM coding config: MCP, skills, rules, and agents.
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
@@ -19,6 +19,8 @@ Requires-Dist: pytest-asyncio>=0.23; extra == "dev"
 Requires-Dist: jsonschema>=4.0; extra == "dev"
 Requires-Dist: ruff>=0.8.0; extra == "dev"
 Requires-Dist: mypy>=1.11; extra == "dev"
+Requires-Dist: types-jsonschema>=4.0; extra == "dev"
+Requires-Dist: types-PyYAML>=6.0; extra == "dev"
 Dynamic: license-file
 
 # code-agnostic
@@ -53,9 +55,10 @@ AI coding tools each want config in a different place and format. When you use m
 ~/.config/opencode/               Compiled & synced for OpenCode
 ~/.cursor/                        Compiled & synced for Cursor
 ~/.codex/                         Compiled & synced for Codex
+~/.claude.json and ~/.claude/      Compiled & synced for Claude Code
 ```
 
-Each resource is cross-compiled to the target editor's native format. Rules become `.mdc` files for Cursor, `AGENTS.md` sections for OpenCode/Codex, etc.
+Each resource is cross-compiled to the target editor's native format. Rules become `.mdc` files for Cursor, `AGENTS.md` sections for OpenCode/Codex, and `CLAUDE.local.md` memory for Claude Code.
 
 Legacy single-file rules, `skills/<name>/SKILL.md`, and markdown agents are still supported for migration, but bundle directories are the preferred source format for new config.
 
@@ -94,6 +97,7 @@ code-agnostic import apply -a codex
 # Enable target editors
 code-agnostic apps enable -a cursor
 code-agnostic apps enable -a opencode
+code-agnostic apps enable -a claude
 
 # Preview and apply
 code-agnostic validate
@@ -103,25 +107,25 @@ code-agnostic apply
 
 ## Editor compatibility
 
-| Feature | OpenCode | Cursor | Codex |
-|---------|:--------:|:------:|:-----:|
-| MCP sync | yes | yes | yes |
-| Rules sync (cross-compiled) | yes | yes | yes |
-| Skills sync | yes | yes | yes |
-| Agents sync | yes | yes | yes |
-| Workspace root `AGENTS.md` link | yes | yes | yes |
-| Native repo config include for workspace `AGENTS.md` | yes | -- | -- |
-| Repo/subdir gets shared workspace `AGENTS.md` today | yes | -- | yes |
-| Nested `AGENTS.md` discovery | -- | yes | yes |
-| Workspace propagation | yes | -- | yes |
-| Import from | yes | yes | yes |
-| Interactive import (TUI) | yes | yes | yes |
+| Feature | OpenCode | Cursor | Codex | Claude Code |
+|---------|:--------:|:------:|:-----:|:-----------:|
+| MCP sync | yes | yes | yes | yes |
+| Rules sync (cross-compiled) | yes | yes | yes | yes |
+| Skills sync | yes | yes | yes | yes |
+| Agents sync | yes | yes | yes | yes |
+| Workspace root `AGENTS.md` link | yes | yes | yes | yes |
+| Native repo config include for workspace `AGENTS.md` | yes | -- | -- | -- |
+| Repo/subdir gets shared workspace instructions today | yes | -- | yes | yes |
+| Nested `AGENTS.md` discovery | -- | yes | yes | -- |
+| Workspace propagation | yes | yes | yes | yes |
+| Import from | yes | yes | yes | yes |
+| Interactive import (TUI) | yes | yes | yes | yes |
 
-Cursor workspace propagation is intentionally disabled to avoid duplicate MCP initialization in multi-root workspaces: https://forum.cursor.com/t/mcp-multi-root-workspace-causes-duplicate-mcp-server-initialization-4x-createclient-actions/144003
+Cursor workspace propagation writes repo-local MCP, skills, and agents when those resources exist in the workspace source config.
 
-OpenCode workspace configs include the shared workspace `AGENTS.md` natively via `instructions`, so repos under the workspace get both repo-local and shared workspace instructions. Codex repos receive workspace instructions through a generated `AGENTS.override.md`, which is added to each repo's `.git/info/exclude`.
+OpenCode workspace configs include the shared workspace `AGENTS.md` natively via `instructions`, so repos under the workspace get both repo-local and shared workspace instructions. Codex repos receive workspace instructions through a generated `AGENTS.override.md`, which is added to each repo's `.git/info/exclude`. Claude Code receives workspace instructions through generated `CLAUDE.local.md` files, never by editing committed `CLAUDE.md`.
 
-Cursor documents `AGENTS.md` support in project roots and subdirectories. `code-agnostic` still disables Cursor workspace propagation, so it does not copy or link the shared workspace `AGENTS.md` into child repos; Cursor will load repo-local or nested `AGENTS.md` files that already exist in the opened project. Codex documents nested `AGENTS.md` discovery, but not a native config include for an extra workspace file.
+Cursor documents `AGENTS.md` support in project roots and subdirectories. `code-agnostic` does not copy or link the shared workspace `AGENTS.md` into child repos; Cursor will load repo-local or nested `AGENTS.md` files that already exist in the opened project. Codex documents nested `AGENTS.md` discovery, but not a native config include for an extra workspace file.
 
 ## Features
 
@@ -195,7 +199,9 @@ code-agnostic plan
 code-agnostic apply
 ```
 
-Global skills live under `~/.config/code-agnostic/skills`. Workspace-local skills live under `~/.config/code-agnostic/workspaces/<name>/skills` and can be inspected with `code-agnostic skills list -w <name>`. Codex generated skill outputs are written to `~/.agents/skills`, while Codex agents and config remain under `~/.codex`.
+Global skills live under `~/.config/code-agnostic/skills`. Workspace-local skills live under `~/.config/code-agnostic/workspaces/<name>/skills` and can be inspected with `code-agnostic skills list -w <name>`. Codex generated skill outputs are written to `~/.agents/skills`, while Codex agents and config remain under `~/.codex`. Claude Code generated skills and agents are written under `~/.claude/skills` and `~/.claude/agents`, with workspace copies under repo-local `.claude/skills` and `.claude/agents`.
+
+Project-local skills are not first-class source inputs in `code-agnostic` yet. If a target app discovers repo-local skill folders such as `.agents/skills`, `.opencode/skills`, or user-created `.claude/skills`, treat those as unmanaged app inputs. Workspace sync writes only the exact generated paths recorded in `.sync-state.json`.
 
 Planned convenience command:
 
@@ -207,9 +213,9 @@ That command should copy the skill into the source of truth and then run the nor
 
 ### Workspaces
 
-Register workspace directories. Workspace rules are compiled into a canonical `AGENTS.md` at the workspace root. Repos keep their own repo-specific `AGENTS.md`; Codex receives the workspace rules through generated, git-excluded `AGENTS.override.md` files, while OpenCode workspace configs reference the shared workspace file through `instructions`. Repo-local app config, skills, and agents are propagated for OpenCode and Codex.
+Register workspace directories. Workspace rules are compiled into a canonical `AGENTS.md` at the workspace root. Repos keep their own repo-specific `AGENTS.md`; Codex receives the workspace rules through generated, git-excluded `AGENTS.override.md` files, while OpenCode workspace configs reference the shared workspace file through `instructions`. Claude receives generated `CLAUDE.local.md` files and project MCP entries in `~/.claude.json["projects"][absolute_repo_path]["mcpServers"]`. Repo-local app config, skills, and agents are propagated for OpenCode, Cursor, Codex, and Claude.
 
-`.cursor` workspace propagation is intentionally disabled to avoid duplicate MCP initialization when opening multi-root workspaces in Cursor (related issue: https://forum.cursor.com/t/mcp-multi-root-workspace-causes-duplicate-mcp-server-initialization-4x-createclient-actions/144003).
+Cursor propagation intentionally stays to repo-local MCP, skills, and agents; it does not copy the shared workspace `AGENTS.md` into child repos.
 
 ```bash
 code-agnostic workspaces add --name myproject --path ~/code/myproject
@@ -234,6 +240,7 @@ Migrate existing config from any supported editor into the hub.
 ```bash
 code-agnostic import plan -a codex
 code-agnostic import apply -a codex
+code-agnostic import plan -a claude
 code-agnostic import apply -a cursor --include mcp --on-conflict overwrite
 code-agnostic import plan -a codex -i    # interactive TUI picker
 ```
@@ -266,7 +273,8 @@ The compiler migration is documented in:
 - [x] Cross-compilation for skills and agents
 - [x] Per-workspace git-exclude customization
 - [x] Interactive TUI for import selection
-- [ ] Claude Code support
+- [x] Claude Code support
+- [ ] Project-scoped skill installs and sync
 - [ ] `rules add` / `skills add` / `agents add` commands (open `$EDITOR` with template)
 - [ ] Planner integration for cross-compiled skills and agents
 - [ ] Shell auto-complete
@@ -279,10 +287,37 @@ uv sync --dev
 uv run pytest
 ```
 
+Before pushing release-prep work, run the supported Python matrix locally. Tox
+delegates each environment to `uv run --python`, so `uv` can provide the
+requested interpreter when it is not already installed:
+
+```bash
+uvx tox run -p auto
+uvx tox run -e uv310 -- tests/test_version.py -q
+```
+
+For a hermetic Linux matrix that does not depend on locally installed Python
+versions, run the Docker matrix:
+
+```bash
+./scripts/run-docker-matrix.sh
+./scripts/run-docker-matrix.sh tests/test_version.py -q
+```
+
+Limit the Docker matrix while iterating:
+
+```bash
+PYTHON_VERSIONS="3.10 3.14" ./scripts/run-docker-matrix.sh tests/test_version.py -q
+```
+
+The release gate still requires GitHub Actions to pass because the published
+workflow is the source of truth for OS coverage across Ubuntu, macOS, and
+Windows on every supported Python version.
+
 Real app-ingestion E2E is gated because it requires installed target CLIs and
 uses each tool's own introspection surface:
 
 ```bash
 CODE_AGNOSTIC_REAL_APP_E2E=1 uv run pytest tests/e2e/test_real_app_ingestion_e2e.py -q
-CODE_AGNOSTIC_REAL_APP_E2E=1 CODE_AGNOSTIC_REAL_APP_TARGETS=codex,opencode uv run pytest tests/e2e/test_real_app_ingestion_e2e.py -q
+CODE_AGNOSTIC_REAL_APP_E2E=1 CODE_AGNOSTIC_REAL_APP_TARGETS=codex,opencode,claude uv run pytest tests/e2e/test_real_app_ingestion_e2e.py -q
 ```

{code_agnostic-0.3.5 → code_agnostic-0.3.8}/README.md

@@ -30,9 +30,10 @@ AI coding tools each want config in a different place and format. When you use m
 ~/.config/opencode/               Compiled & synced for OpenCode
 ~/.cursor/                        Compiled & synced for Cursor
 ~/.codex/                         Compiled & synced for Codex
+~/.claude.json and ~/.claude/      Compiled & synced for Claude Code
 ```
 
-Each resource is cross-compiled to the target editor's native format. Rules become `.mdc` files for Cursor, `AGENTS.md` sections for OpenCode/Codex, etc.
+Each resource is cross-compiled to the target editor's native format. Rules become `.mdc` files for Cursor, `AGENTS.md` sections for OpenCode/Codex, and `CLAUDE.local.md` memory for Claude Code.
 
 Legacy single-file rules, `skills/<name>/SKILL.md`, and markdown agents are still supported for migration, but bundle directories are the preferred source format for new config.
 
@@ -71,6 +72,7 @@ code-agnostic import apply -a codex
 # Enable target editors
 code-agnostic apps enable -a cursor
 code-agnostic apps enable -a opencode
+code-agnostic apps enable -a claude
 
 # Preview and apply
 code-agnostic validate
@@ -80,25 +82,25 @@ code-agnostic apply
 
 ## Editor compatibility
 
-| Feature | OpenCode | Cursor | Codex |
-|---------|:--------:|:------:|:-----:|
-| MCP sync | yes | yes | yes |
-| Rules sync (cross-compiled) | yes | yes | yes |
-| Skills sync | yes | yes | yes |
-| Agents sync | yes | yes | yes |
-| Workspace root `AGENTS.md` link | yes | yes | yes |
-| Native repo config include for workspace `AGENTS.md` | yes | -- | -- |
-| Repo/subdir gets shared workspace `AGENTS.md` today | yes | -- | yes |
-| Nested `AGENTS.md` discovery | -- | yes | yes |
-| Workspace propagation | yes | -- | yes |
-| Import from | yes | yes | yes |
-| Interactive import (TUI) | yes | yes | yes |
+| Feature | OpenCode | Cursor | Codex | Claude Code |
+|---------|:--------:|:------:|:-----:|:-----------:|
+| MCP sync | yes | yes | yes | yes |
+| Rules sync (cross-compiled) | yes | yes | yes | yes |
+| Skills sync | yes | yes | yes | yes |
+| Agents sync | yes | yes | yes | yes |
+| Workspace root `AGENTS.md` link | yes | yes | yes | yes |
+| Native repo config include for workspace `AGENTS.md` | yes | -- | -- | -- |
+| Repo/subdir gets shared workspace instructions today | yes | -- | yes | yes |
+| Nested `AGENTS.md` discovery | -- | yes | yes | -- |
+| Workspace propagation | yes | yes | yes | yes |
+| Import from | yes | yes | yes | yes |
+| Interactive import (TUI) | yes | yes | yes | yes |
 
-Cursor workspace propagation is intentionally disabled to avoid duplicate MCP initialization in multi-root workspaces: https://forum.cursor.com/t/mcp-multi-root-workspace-causes-duplicate-mcp-server-initialization-4x-createclient-actions/144003
+Cursor workspace propagation writes repo-local MCP, skills, and agents when those resources exist in the workspace source config.
 
-OpenCode workspace configs include the shared workspace `AGENTS.md` natively via `instructions`, so repos under the workspace get both repo-local and shared workspace instructions. Codex repos receive workspace instructions through a generated `AGENTS.override.md`, which is added to each repo's `.git/info/exclude`.
+OpenCode workspace configs include the shared workspace `AGENTS.md` natively via `instructions`, so repos under the workspace get both repo-local and shared workspace instructions. Codex repos receive workspace instructions through a generated `AGENTS.override.md`, which is added to each repo's `.git/info/exclude`. Claude Code receives workspace instructions through generated `CLAUDE.local.md` files, never by editing committed `CLAUDE.md`.
 
-Cursor documents `AGENTS.md` support in project roots and subdirectories. `code-agnostic` still disables Cursor workspace propagation, so it does not copy or link the shared workspace `AGENTS.md` into child repos; Cursor will load repo-local or nested `AGENTS.md` files that already exist in the opened project. Codex documents nested `AGENTS.md` discovery, but not a native config include for an extra workspace file.
+Cursor documents `AGENTS.md` support in project roots and subdirectories. `code-agnostic` does not copy or link the shared workspace `AGENTS.md` into child repos; Cursor will load repo-local or nested `AGENTS.md` files that already exist in the opened project. Codex documents nested `AGENTS.md` discovery, but not a native config include for an extra workspace file.
 
 ## Features
 
@@ -172,7 +174,9 @@ code-agnostic plan
 code-agnostic apply
 ```
 
-Global skills live under `~/.config/code-agnostic/skills`. Workspace-local skills live under `~/.config/code-agnostic/workspaces/<name>/skills` and can be inspected with `code-agnostic skills list -w <name>`. Codex generated skill outputs are written to `~/.agents/skills`, while Codex agents and config remain under `~/.codex`.
+Global skills live under `~/.config/code-agnostic/skills`. Workspace-local skills live under `~/.config/code-agnostic/workspaces/<name>/skills` and can be inspected with `code-agnostic skills list -w <name>`. Codex generated skill outputs are written to `~/.agents/skills`, while Codex agents and config remain under `~/.codex`. Claude Code generated skills and agents are written under `~/.claude/skills` and `~/.claude/agents`, with workspace copies under repo-local `.claude/skills` and `.claude/agents`.
+
+Project-local skills are not first-class source inputs in `code-agnostic` yet. If a target app discovers repo-local skill folders such as `.agents/skills`, `.opencode/skills`, or user-created `.claude/skills`, treat those as unmanaged app inputs. Workspace sync writes only the exact generated paths recorded in `.sync-state.json`.
 
 Planned convenience command:
 
@@ -184,9 +188,9 @@ That command should copy the skill into the source of truth and then run the nor
 
 ### Workspaces
 
-Register workspace directories. Workspace rules are compiled into a canonical `AGENTS.md` at the workspace root. Repos keep their own repo-specific `AGENTS.md`; Codex receives the workspace rules through generated, git-excluded `AGENTS.override.md` files, while OpenCode workspace configs reference the shared workspace file through `instructions`. Repo-local app config, skills, and agents are propagated for OpenCode and Codex.
+Register workspace directories. Workspace rules are compiled into a canonical `AGENTS.md` at the workspace root. Repos keep their own repo-specific `AGENTS.md`; Codex receives the workspace rules through generated, git-excluded `AGENTS.override.md` files, while OpenCode workspace configs reference the shared workspace file through `instructions`. Claude receives generated `CLAUDE.local.md` files and project MCP entries in `~/.claude.json["projects"][absolute_repo_path]["mcpServers"]`. Repo-local app config, skills, and agents are propagated for OpenCode, Cursor, Codex, and Claude.
 
-`.cursor` workspace propagation is intentionally disabled to avoid duplicate MCP initialization when opening multi-root workspaces in Cursor (related issue: https://forum.cursor.com/t/mcp-multi-root-workspace-causes-duplicate-mcp-server-initialization-4x-createclient-actions/144003).
+Cursor propagation intentionally stays to repo-local MCP, skills, and agents; it does not copy the shared workspace `AGENTS.md` into child repos.
 
 ```bash
 code-agnostic workspaces add --name myproject --path ~/code/myproject
@@ -211,6 +215,7 @@ Migrate existing config from any supported editor into the hub.
 ```bash
 code-agnostic import plan -a codex
 code-agnostic import apply -a codex
+code-agnostic import plan -a claude
 code-agnostic import apply -a cursor --include mcp --on-conflict overwrite
 code-agnostic import plan -a codex -i    # interactive TUI picker
 ```
@@ -243,7 +248,8 @@ The compiler migration is documented in:
 - [x] Cross-compilation for skills and agents
 - [x] Per-workspace git-exclude customization
 - [x] Interactive TUI for import selection
-- [ ] Claude Code support
+- [x] Claude Code support
+- [ ] Project-scoped skill installs and sync
 - [ ] `rules add` / `skills add` / `agents add` commands (open `$EDITOR` with template)
 - [ ] Planner integration for cross-compiled skills and agents
 - [ ] Shell auto-complete
@@ -256,10 +262,37 @@ uv sync --dev
 uv run pytest
 ```
 
+Before pushing release-prep work, run the supported Python matrix locally. Tox
+delegates each environment to `uv run --python`, so `uv` can provide the
+requested interpreter when it is not already installed:
+
+```bash
+uvx tox run -p auto
+uvx tox run -e uv310 -- tests/test_version.py -q
+```
+
+For a hermetic Linux matrix that does not depend on locally installed Python
+versions, run the Docker matrix:
+
+```bash
+./scripts/run-docker-matrix.sh
+./scripts/run-docker-matrix.sh tests/test_version.py -q
+```
+
+Limit the Docker matrix while iterating:
+
+```bash
+PYTHON_VERSIONS="3.10 3.14" ./scripts/run-docker-matrix.sh tests/test_version.py -q
+```
+
+The release gate still requires GitHub Actions to pass because the published
+workflow is the source of truth for OS coverage across Ubuntu, macOS, and
+Windows on every supported Python version.
+
 Real app-ingestion E2E is gated because it requires installed target CLIs and
 uses each tool's own introspection surface:
 
 ```bash
 CODE_AGNOSTIC_REAL_APP_E2E=1 uv run pytest tests/e2e/test_real_app_ingestion_e2e.py -q
-CODE_AGNOSTIC_REAL_APP_E2E=1 CODE_AGNOSTIC_REAL_APP_TARGETS=codex,opencode uv run pytest tests/e2e/test_real_app_ingestion_e2e.py -q
+CODE_AGNOSTIC_REAL_APP_E2E=1 CODE_AGNOSTIC_REAL_APP_TARGETS=codex,opencode,claude uv run pytest tests/e2e/test_real_app_ingestion_e2e.py -q
 ```

{code_agnostic-0.3.5 → code_agnostic-0.3.8}/code_agnostic/__init__.py

@@ -1,3 +1,3 @@
 __all__ = ["__version__"]
 
-__version__ = "0.3.5"
+__version__ = "0.3.8"

code_agnostic-0.3.8/code_agnostic/agents/claude.py

@@ -0,0 +1,67 @@
+"""Claude Code subagent Markdown conversion."""
+
+from __future__ import annotations
+
+import re
+from pathlib import Path
+from typing import Any
+
+import yaml  # type: ignore[import-untyped]
+
+from code_agnostic.agents.models import Agent
+
+_SAFE_FILE_STEM_RE = re.compile(r"[^A-Za-z0-9_-]+")
+
+
+def normalize_claude_agent_filename(name: str, fallback: str) -> str:
+    candidate = name.strip() or fallback.strip()
+    normalized = _SAFE_FILE_STEM_RE.sub("-", candidate).strip("-_")
+    return normalized or fallback
+
+
+def serialize_claude_agent(agent: Agent) -> str:
+    fm: dict[str, Any] = {}
+    if agent.metadata.name:
+        fm["name"] = agent.metadata.name
+    else:
+        fm["name"] = agent.name
+
+    description = agent.metadata.description or agent.metadata.name or agent.name
+    if description:
+        fm["description"] = description
+
+    model = agent.metadata.effective_value("claude", "model")
+    if model:
+        fm["model"] = model
+    reasoning_effort = agent.metadata.effective_value("claude", "reasoning_effort")
+    if reasoning_effort:
+        fm["effort"] = reasoning_effort
+
+    for key, value in agent.metadata.app_passthrough(
+        "claude",
+        consumed_keys={
+            "model",
+            "reasoning_effort",
+            "sandbox_mode",
+            "nickname_candidates",
+        },
+    ).items():
+        if key in fm:
+            continue
+        fm[key] = value
+
+    parts = [
+        "---",
+        yaml.dump(fm, default_flow_style=False, sort_keys=False).rstrip(),
+        "---",
+        "",
+        agent.content,
+    ]
+    return "\n".join(parts)
+
+
+def claude_agent_target_path(target_dir: Path, agent: Agent) -> Path:
+    return (
+        target_dir
+        / f"{normalize_claude_agent_filename(agent.metadata.name, agent.name)}.md"
+    )

{code_agnostic-0.3.5 → code_agnostic-0.3.8}/code_agnostic/agents/codex.py

@@ -69,10 +69,13 @@ def serialize_codex_agent(agent: Agent) -> str:
     description = agent.metadata.description or agent.metadata.name or agent.name
 
     doc = tomlkit.document()
-    doc.add("name", agent.metadata.name or agent.name)
-    doc.add("description", description)
+    doc.add("name", tomlkit.item(agent.metadata.name or agent.name))
+    doc.add("description", tomlkit.item(description))
     if agent.metadata.nickname_candidates:
-        doc.add("nickname_candidates", list(agent.metadata.nickname_candidates))
+        doc.add(
+            "nickname_candidates",
+            tomlkit.item(list(agent.metadata.nickname_candidates)),
+        )
     model = agent.metadata.effective_value("codex", "model")
     if model:
         doc.add("model", model)

{code_agnostic-0.3.5 → code_agnostic-0.3.8}/code_agnostic/agents/compilers.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 
 from abc import ABC, abstractmethod
 
+from code_agnostic.agents.claude import serialize_claude_agent
 from code_agnostic.agents.codex import serialize_codex_agent
 from code_agnostic.agents.models import Agent
 from code_agnostic.agents.opencode import serialize_opencode_agent
@@ -35,3 +36,10 @@ class CodexAgentCompiler(IAgentCompiler):
 
     def compile(self, agent: Agent) -> str:
         return serialize_codex_agent(agent)
+
+
+class ClaudeAgentCompiler(IAgentCompiler):
+    """Cross-compile for Claude Code subagents."""
+
+    def compile(self, agent: Agent) -> str:
+        return serialize_claude_agent(agent)

{code_agnostic-0.3.5 → code_agnostic-0.3.8}/code_agnostic/agents/parser.py

@@ -19,7 +19,7 @@ from code_agnostic.agents.models import (
 from code_agnostic.spec.loaders import load_agent_bundle
 
 _FRONTMATTER_RE = re.compile(r"^---\s*\n(.*?)\n---\s*\n", re.DOTALL)
-_APP_OVERRIDE_PREFIXES = ("cursor", "codex", "opencode")
+_APP_OVERRIDE_PREFIXES = ("cursor", "codex", "opencode", "claude")
 
 
 def parse_agent(path: Path) -> Agent:

{code_agnostic-0.3.5 → code_agnostic-0.3.8}/code_agnostic/apps/app_id.py

@@ -2,6 +2,8 @@ from enum import Enum
 from dataclasses import dataclass
 
 from code_agnostic.constants import (
+    CLAUDE_CONFIG_FILENAME,
+    CLAUDE_PROJECT_DIRNAME,
     CODEX_CONFIG_FILENAME,
     CODEX_PROJECT_DIRNAME,
     CURSOR_CONFIG_FILENAME,
@@ -16,6 +18,7 @@ class AppId(str, Enum):
     OPENCODE = "opencode"
     CURSOR = "cursor"
     CODEX = "codex"
+    CLAUDE = "claude"
 
 
 @dataclass(frozen=True)
@@ -60,7 +63,7 @@ APP_CATALOG: dict[AppId, AppMetadata] = {
         toggleable=True,
         importable=True,
         supports_import_agents=True,
-        supports_workspace_propagation=False,
+        supports_workspace_propagation=True,
         project_dir_name=CURSOR_PROJECT_DIRNAME,
         config_filename=CURSOR_CONFIG_FILENAME,
     ),
@@ -75,6 +78,17 @@ APP_CATALOG: dict[AppId, AppMetadata] = {
         project_dir_name=CODEX_PROJECT_DIRNAME,
         config_filename=CODEX_CONFIG_FILENAME,
     ),
+    AppId.CLAUDE: AppMetadata(
+        app_id=AppId.CLAUDE,
+        label="Claude Code",
+        targetable=True,
+        toggleable=True,
+        importable=True,
+        supports_import_agents=True,
+        supports_workspace_propagation=True,
+        project_dir_name=CLAUDE_PROJECT_DIRNAME,
+        config_filename=CLAUDE_CONFIG_FILENAME,
+    ),
 }
 
 

code_agnostic-0.3.8/code_agnostic/apps/claude/__init__.py

@@ -0,0 +1 @@
+"""Claude Code app support."""

code_agnostic-0.3.8/code_agnostic/apps/claude/config_repository.py

@@ -0,0 +1,59 @@
+from pathlib import Path
+from typing import Any
+
+from code_agnostic.apps.common.interfaces.repositories import IAppConfigRepository
+from code_agnostic.constants import (
+    AGENTS_DIRNAME,
+    CLAUDE_CONFIG_FILENAME,
+    CLAUDE_PROJECT_DIRNAME,
+    SKILLS_DIRNAME,
+)
+from code_agnostic.errors import InvalidConfigSchemaError, InvalidJsonFormatError
+from code_agnostic.utils import read_json_safe, write_json
+
+
+class ClaudeConfigRepository(IAppConfigRepository):
+    def __init__(
+        self, root: Path | None = None, config_path: Path | None = None
+    ) -> None:
+        self._root = root or (Path.home() / CLAUDE_PROJECT_DIRNAME)
+        self._config_path = config_path or (Path.home() / CLAUDE_CONFIG_FILENAME)
+
+    @property
+    def root(self) -> Path:
+        return self._root
+
+    @property
+    def config_path(self) -> Path:
+        return self._config_path
+
+    @property
+    def skills_dir(self) -> Path:
+        return self.root / SKILLS_DIRNAME
+
+    @property
+    def agents_dir(self) -> Path:
+        return self.root / AGENTS_DIRNAME
+
+    def load_config(self) -> dict[str, Any]:
+        payload, error = read_json_safe(self.config_path)
+        if error is not None:
+            raise InvalidJsonFormatError(self.config_path, error)
+        if payload is None:
+            return {}
+        if not isinstance(payload, dict):
+            raise InvalidConfigSchemaError(self.config_path, "must be a JSON object")
+        return payload
+
+    def save_config(self, payload: dict[str, Any]) -> None:
+        write_json(self.config_path, payload)
+
+    def load_mcp_payload(self) -> dict[str, Any]:
+        payload = self.load_config()
+        mcp = payload.get("mcpServers")
+        return mcp if isinstance(mcp, dict) else {}
+
+    def save_mcp_payload(self, payload: dict[str, Any]) -> None:
+        config = self.load_config()
+        config["mcpServers"] = payload
+        self.save_config(config)

code_agnostic-0.3.8/code_agnostic/apps/claude/mapper.py

@@ -0,0 +1,86 @@
+from copy import deepcopy
+from typing import Any
+
+from code_agnostic.apps.common.interfaces.mapper import IAppMCPMapper
+from code_agnostic.apps.common.models import MCPServerDTO, MCPServerType
+
+
+def _as_list(value: Any) -> list[str]:
+    if isinstance(value, list):
+        return [str(item) for item in value]
+    if isinstance(value, str):
+        return [value]
+    return []
+
+
+def _as_str_dict(value: Any) -> dict[str, str]:
+    return {str(k): str(v) for k, v in value.items()} if isinstance(value, dict) else {}
+
+
+def _timeout(value: Any) -> int | None:
+    if isinstance(value, int) and not isinstance(value, bool):
+        return value
+    return None
+
+
+class ClaudeMCPMapper(IAppMCPMapper):
+    def to_common(self, payload: dict[str, Any]) -> dict[str, MCPServerDTO]:
+        mapped: dict[str, MCPServerDTO] = {}
+        for name, server in payload.items():
+            if not isinstance(server, dict):
+                continue
+
+            server_type = server.get("type")
+            command = server.get("command")
+            if server_type == "stdio" or isinstance(command, str):
+                if not isinstance(command, str) or not command:
+                    continue
+                mapped[name] = MCPServerDTO(
+                    name=name,
+                    type=MCPServerType.STDIO,
+                    command=command,
+                    args=_as_list(server.get("args")),
+                    env=_as_str_dict(server.get("env")),
+                    headers=_as_str_dict(server.get("headers")),
+                    timeout_ms=_timeout(server.get("timeout")),
+                )
+                continue
+
+            url = server.get("url")
+            if not isinstance(url, str) or not url:
+                continue
+            mapped[name] = MCPServerDTO(
+                name=name,
+                type=MCPServerType.HTTP,
+                url=url,
+                env=_as_str_dict(server.get("env")),
+                headers=_as_str_dict(server.get("headers")),
+                timeout_ms=_timeout(server.get("timeout")),
+            )
+        return mapped
+
+    def from_common(self, servers: dict[str, MCPServerDTO]) -> dict[str, Any]:
+        mapped: dict[str, Any] = {}
+        for name, server in servers.items():
+            out: dict[str, Any] = {}
+            if server.type == MCPServerType.STDIO:
+                if not server.command:
+                    continue
+                out["type"] = "stdio"
+                out["command"] = server.command
+                if server.args:
+                    out["args"] = deepcopy(server.args)
+            else:
+                if not server.url:
+                    continue
+                out["type"] = "http"
+                out["url"] = server.url
+
+            if server.env:
+                out["env"] = deepcopy(server.env)
+            if server.headers:
+                out["headers"] = deepcopy(server.headers)
+            if server.timeout_ms is not None:
+                out["timeout"] = server.timeout_ms
+            mapped[name] = out
+        return mapped