codeforerunner 0.4.3__tar.gz → 0.4.4__tar.gz

{codeforerunner-0.4.3/src/codeforerunner.egg-info → codeforerunner-0.4.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: codeforerunner
-Version: 0.4.3
+Version: 0.4.4
 Summary: Model-agnostic repository documentation tooling (prompt-first; thin CLI).
 Author: Derek Palmer
 License-Expression: LicenseRef-Codeforerunner-SAL-0.1
@@ -29,11 +29,11 @@ Dynamic: license-file
 
 # codeForerunner
 
-Model-agnostic repository documentation tooling. Ships a prompt pack for codebase analysis and doc generation, a thin Python CLI, an MCP server, drift-detection rules that keep docs honest — and native slash-command skills for Claude Code, Codex, Gemini CLI, and other agent CLIs.
+[![Socket Badge](https://badge.socket.dev/npm/package/codeforerunner/0.4.3)](https://badge.socket.dev/npm/package/codeforerunner/0.4.3)
 
-## Two modes
+Model-agnostic repository documentation tooling. Ships a prompt pack for codebase analysis and doc generation, a thin Python CLI, an MCP server, drift-detection rules that keep docs honest — and native slash-command skills for Claude Code, Codex, Gemini CLI, and other agent CLIs.
 
-### Mode A — Agent skill (recommended, no API key required)
+## Install
 
 Install forerunner's prompt pack as skills into your agent CLI. Each documentation task becomes a slash command (`/forerunner-readme`, `/forerunner-check`, etc.) available inside Claude Code, Codex, Gemini CLI, and other agents. Authentication is handled by your existing agent subscription — no separate API key needed.
 
@@ -58,26 +58,9 @@ Then in your agent:
 /forerunner-scan        ← scan the repo first
 /forerunner-readme      ← generate README
 /forerunner-check       ← detect doc drift
+/forerunner-refresh     ← scan + update all stale docs
 ```
 
-### Mode B — Direct API (needs API key or Ollama)
-
-Install the Python CLI and call your provider directly. Works without any agent CLI installed.
-
-```bash
-pipx install codeforerunner   # recommended
-pip install codeforerunner    # alternative
-```
-
-Configure a provider (or start Ollama for keyless local generation):
-
-```bash
-export ANTHROPIC_API_KEY=sk-...
-forerunner generate readme --stream
-```
-
-If no API key and no `--provider` flag, forerunner auto-detects Ollama at `localhost:11434` and falls back to local mode.
-
 ## Slash commands
 
 | Command | Task | Purpose |
@@ -94,14 +77,17 @@ If no API key and no `--provider` flag, forerunner auto-detects Ollama at `local
 | `/forerunner-audit` | `audit` | Security and dependency audit |
 | `/forerunner-changelog` | `changelog` | Generate changelog from git log |
 | `/forerunner-init` | `init-agent-onboarding` | Bootstrap or refresh AGENTS.md |
+| `/forerunner-refresh` | `refresh` | Scan + check + update all stale docs in one pass |
 
-Slash command availability depends on the agent CLI. Claude Code, Codex, and Gemini CLI support all 12 commands after install.
+Slash command availability depends on the agent CLI. Claude Code, Codex, and Gemini CLI support all commands after install.
 
 ## Skill install options
 
 | Flag | Effect |
 |------|--------|
-| `./install.sh` | Auto-detect all agents, install all skills |
+| `./install.sh` | Auto-detect all agents, prompt global vs local, install all skills |
+| `./install.sh --global` | Skip prompt, install to global agent dirs (all projects) |
+| `./install.sh --local` | Skip prompt, install to `.claude/skills/` and `.agents/skills/` in cwd |
 | `./install.sh --only claude` | Claude Code only |
 | `./install.sh --only codex` | Codex only |
 | `./install.sh --only gemini` | Gemini CLI only |
@@ -120,65 +106,54 @@ pip install codeforerunner
 | `forerunner init` | Resolve agent-onboarding bundle to stdout. |
 | `forerunner scan` | Resolve scan bundle to stdout. |
 | `forerunner doc <task>` | Resolve `base + partials + task` bundle to stdout. |
+| `forerunner refresh` | Output scan + check + all doc-task bundles in sequence for a full doc refresh. |
 | `forerunner check` | Run drift-detection rules; no-op without `forerunner.config.yaml`. |
-| `forerunner generate <task>` | Call configured provider directly. Add `--stream` for token-by-token output. Falls back to Ollama automatically when no API key is configured. |
-| `forerunner doctor` | Health report: skill parity, config, provider key, local-mode status. Add `--fix` to write a starter config. |
+| `forerunner doctor` | Health report: skill parity, config. Add `--fix` to write a starter config. |
 | `forerunner mcp-server` | Serve prompt bundles as MCP tools over stdio (JSON-RPC 2.0). |
 | `forerunner install <agent>` | Install canonical skill into agent-specific directory. Add `--all` for all per-task skills. |
 
-## Prompt pack
-
-Prompts are bundled inside the package at `src/codeforerunner/prompts/`.
-
-```text
-prompts/
-├── system/base.md
-├── partials/
-│   ├── context-format.md
-│   ├── output-rules.md
-│   └── stack-hints.md
-└── tasks/
-    ├── scan.md          api-docs.md    audit.md
-    ├── readme.md        diagrams.md    changelog.md
-    ├── check.md         flows.md       version-audit.md
-    ├── review.md        stack-docs.md
-    └── init-agent-onboarding.md
-```
-
-## Quick start (agent skill mode)
+## Quick start
 
 ```bash
 # Install skills into Claude Code
 curl -fsSL https://raw.githubusercontent.com/derek-palmer/codeforerunner/main/install.sh | bash
 
 # In Claude Code:
-# /forerunner-scan    → scans your repo
-# /forerunner-readme  → generates README.md
-# /forerunner-check   → checks for doc drift
+# /forerunner-scan     → scans your repo
+# /forerunner-readme   → generates README.md
+# /forerunner-refresh  → updates all stale docs
+# /forerunner-check    → checks for doc drift
 ```
 
-## Quick start (direct API mode)
-
-```bash
-# 1. Install and configure
-pip install codeforerunner
-export ANTHROPIC_API_KEY=sk-...
+## GitHub Action
 
-# 2. Run a task
-forerunner generate readme --stream
+Add doc-drift detection to any repo's CI — fails the PR if docs contradict repo state.
 
-# 3. Enable drift detection
-forerunner doctor --fix        # writes forerunner.config.yaml
-forerunner check               # run any time or as pre-commit hook
+```yaml
+# .github/workflows/doc-check.yml
+name: Doc Check
+on: [push, pull_request]
+
+jobs:
+  doc-check:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6.0.2
+      - uses: derek-palmer/codeforerunner@v0.4.3
+        with:
+          fail-on-drift: "true"   # set "false" to warn-only
 ```
 
-## GitHub Action
+No-op when `forerunner.config.yaml` is absent — safe to add before configuring rules.
 
-```yaml
-- uses: derek-palmer/codeforerunner@v0.4.2
-```
+**Inputs**
 
-No-op when `forerunner.config.yaml` is absent.
+| Input | Default | Description |
+|-------|---------|-------------|
+| `version` | `latest` | `codeforerunner` version to install |
+| `python-version` | `3.11` | Python version |
+| `repo` | workspace root | Path to check |
+| `fail-on-drift` | `true` | Exit non-zero on drift |
 
 ## Configuration
 
@@ -191,10 +166,7 @@ forerunner doctor --fix
 ### Config fields
 
 ```yaml
-provider: anthropic          # anthropic | openai | google | ollama
-model: claude-opus-4-7
-api_key_env:
-  anthropic: ANTHROPIC_API_KEY
+approaching_eol_threshold_months: 6
 
 tasks:
   check:
@@ -237,16 +209,24 @@ tasks:
 
 See `examples/mcp/` for Claude Desktop and mcp-cli wiring examples.
 
-## Providers
+## Prompt pack
 
-`forerunner generate` supports four providers. When no provider is explicitly configured and no API key is found, forerunner probes `localhost:11434` and falls back to Ollama automatically.
+Prompts are bundled inside the package at `src/codeforerunner/prompts/`.
 
-| Provider | Env var | Default model |
-|----------|---------|---------------|
-| `anthropic` | `ANTHROPIC_API_KEY` | `claude-opus-4-7` |
-| `openai` | `OPENAI_API_KEY` | `gpt-4o` |
-| `google` | `GOOGLE_API_KEY` | `gemini-2.5-pro` |
-| `ollama` | `OLLAMA_HOST` (optional) | `llama3` |
+```text
+prompts/
+├── system/base.md
+├── partials/
+│   ├── context-format.md
+│   ├── output-rules.md
+│   └── stack-hints.md
+└── tasks/
+    ├── scan.md          api-docs.md    audit.md
+    ├── readme.md        diagrams.md    changelog.md
+    ├── check.md         flows.md       version-audit.md
+    ├── review.md        stack-docs.md  refresh.md
+    └── init-agent-onboarding.md
+```
 
 ## Docs and spec
 

{codeforerunner-0.4.3 → codeforerunner-0.4.4}/README.md

@@ -2,11 +2,11 @@
 
 # codeForerunner
 
-Model-agnostic repository documentation tooling. Ships a prompt pack for codebase analysis and doc generation, a thin Python CLI, an MCP server, drift-detection rules that keep docs honest — and native slash-command skills for Claude Code, Codex, Gemini CLI, and other agent CLIs.
+[![Socket Badge](https://badge.socket.dev/npm/package/codeforerunner/0.4.3)](https://badge.socket.dev/npm/package/codeforerunner/0.4.3)
 
-## Two modes
+Model-agnostic repository documentation tooling. Ships a prompt pack for codebase analysis and doc generation, a thin Python CLI, an MCP server, drift-detection rules that keep docs honest — and native slash-command skills for Claude Code, Codex, Gemini CLI, and other agent CLIs.
 
-### Mode A — Agent skill (recommended, no API key required)
+## Install
 
 Install forerunner's prompt pack as skills into your agent CLI. Each documentation task becomes a slash command (`/forerunner-readme`, `/forerunner-check`, etc.) available inside Claude Code, Codex, Gemini CLI, and other agents. Authentication is handled by your existing agent subscription — no separate API key needed.
 
@@ -31,26 +31,9 @@ Then in your agent:
 /forerunner-scan        ← scan the repo first
 /forerunner-readme      ← generate README
 /forerunner-check       ← detect doc drift
+/forerunner-refresh     ← scan + update all stale docs
 ```
 
-### Mode B — Direct API (needs API key or Ollama)
-
-Install the Python CLI and call your provider directly. Works without any agent CLI installed.
-
-```bash
-pipx install codeforerunner   # recommended
-pip install codeforerunner    # alternative
-```
-
-Configure a provider (or start Ollama for keyless local generation):
-
-```bash
-export ANTHROPIC_API_KEY=sk-...
-forerunner generate readme --stream
-```
-
-If no API key and no `--provider` flag, forerunner auto-detects Ollama at `localhost:11434` and falls back to local mode.
-
 ## Slash commands
 
 | Command | Task | Purpose |
@@ -67,14 +50,17 @@ If no API key and no `--provider` flag, forerunner auto-detects Ollama at `local
 | `/forerunner-audit` | `audit` | Security and dependency audit |
 | `/forerunner-changelog` | `changelog` | Generate changelog from git log |
 | `/forerunner-init` | `init-agent-onboarding` | Bootstrap or refresh AGENTS.md |
+| `/forerunner-refresh` | `refresh` | Scan + check + update all stale docs in one pass |
 
-Slash command availability depends on the agent CLI. Claude Code, Codex, and Gemini CLI support all 12 commands after install.
+Slash command availability depends on the agent CLI. Claude Code, Codex, and Gemini CLI support all commands after install.
 
 ## Skill install options
 
 | Flag | Effect |
 |------|--------|
-| `./install.sh` | Auto-detect all agents, install all skills |
+| `./install.sh` | Auto-detect all agents, prompt global vs local, install all skills |
+| `./install.sh --global` | Skip prompt, install to global agent dirs (all projects) |
+| `./install.sh --local` | Skip prompt, install to `.claude/skills/` and `.agents/skills/` in cwd |
 | `./install.sh --only claude` | Claude Code only |
 | `./install.sh --only codex` | Codex only |
 | `./install.sh --only gemini` | Gemini CLI only |
@@ -93,65 +79,54 @@ pip install codeforerunner
 | `forerunner init` | Resolve agent-onboarding bundle to stdout. |
 | `forerunner scan` | Resolve scan bundle to stdout. |
 | `forerunner doc <task>` | Resolve `base + partials + task` bundle to stdout. |
+| `forerunner refresh` | Output scan + check + all doc-task bundles in sequence for a full doc refresh. |
 | `forerunner check` | Run drift-detection rules; no-op without `forerunner.config.yaml`. |
-| `forerunner generate <task>` | Call configured provider directly. Add `--stream` for token-by-token output. Falls back to Ollama automatically when no API key is configured. |
-| `forerunner doctor` | Health report: skill parity, config, provider key, local-mode status. Add `--fix` to write a starter config. |
+| `forerunner doctor` | Health report: skill parity, config. Add `--fix` to write a starter config. |
 | `forerunner mcp-server` | Serve prompt bundles as MCP tools over stdio (JSON-RPC 2.0). |
 | `forerunner install <agent>` | Install canonical skill into agent-specific directory. Add `--all` for all per-task skills. |
 
-## Prompt pack
-
-Prompts are bundled inside the package at `src/codeforerunner/prompts/`.
-
-```text
-prompts/
-├── system/base.md
-├── partials/
-│   ├── context-format.md
-│   ├── output-rules.md
-│   └── stack-hints.md
-└── tasks/
-    ├── scan.md          api-docs.md    audit.md
-    ├── readme.md        diagrams.md    changelog.md
-    ├── check.md         flows.md       version-audit.md
-    ├── review.md        stack-docs.md
-    └── init-agent-onboarding.md
-```
-
-## Quick start (agent skill mode)
+## Quick start
 
 ```bash
 # Install skills into Claude Code
 curl -fsSL https://raw.githubusercontent.com/derek-palmer/codeforerunner/main/install.sh | bash
 
 # In Claude Code:
-# /forerunner-scan    → scans your repo
-# /forerunner-readme  → generates README.md
-# /forerunner-check   → checks for doc drift
+# /forerunner-scan     → scans your repo
+# /forerunner-readme   → generates README.md
+# /forerunner-refresh  → updates all stale docs
+# /forerunner-check    → checks for doc drift
 ```
 
-## Quick start (direct API mode)
-
-```bash
-# 1. Install and configure
-pip install codeforerunner
-export ANTHROPIC_API_KEY=sk-...
+## GitHub Action
 
-# 2. Run a task
-forerunner generate readme --stream
+Add doc-drift detection to any repo's CI — fails the PR if docs contradict repo state.
 
-# 3. Enable drift detection
-forerunner doctor --fix        # writes forerunner.config.yaml
-forerunner check               # run any time or as pre-commit hook
+```yaml
+# .github/workflows/doc-check.yml
+name: Doc Check
+on: [push, pull_request]
+
+jobs:
+  doc-check:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6.0.2
+      - uses: derek-palmer/codeforerunner@v0.4.3
+        with:
+          fail-on-drift: "true"   # set "false" to warn-only
 ```
 
-## GitHub Action
+No-op when `forerunner.config.yaml` is absent — safe to add before configuring rules.
 
-```yaml
-- uses: derek-palmer/codeforerunner@v0.4.2
-```
+**Inputs**
 
-No-op when `forerunner.config.yaml` is absent.
+| Input | Default | Description |
+|-------|---------|-------------|
+| `version` | `latest` | `codeforerunner` version to install |
+| `python-version` | `3.11` | Python version |
+| `repo` | workspace root | Path to check |
+| `fail-on-drift` | `true` | Exit non-zero on drift |
 
 ## Configuration
 
@@ -164,10 +139,7 @@ forerunner doctor --fix
 ### Config fields
 
 ```yaml
-provider: anthropic          # anthropic | openai | google | ollama
-model: claude-opus-4-7
-api_key_env:
-  anthropic: ANTHROPIC_API_KEY
+approaching_eol_threshold_months: 6
 
 tasks:
   check:
@@ -210,16 +182,24 @@ tasks:
 
 See `examples/mcp/` for Claude Desktop and mcp-cli wiring examples.
 
-## Providers
+## Prompt pack
 
-`forerunner generate` supports four providers. When no provider is explicitly configured and no API key is found, forerunner probes `localhost:11434` and falls back to Ollama automatically.
+Prompts are bundled inside the package at `src/codeforerunner/prompts/`.
 
-| Provider | Env var | Default model |
-|----------|---------|---------------|
-| `anthropic` | `ANTHROPIC_API_KEY` | `claude-opus-4-7` |
-| `openai` | `OPENAI_API_KEY` | `gpt-4o` |
-| `google` | `GOOGLE_API_KEY` | `gemini-2.5-pro` |
-| `ollama` | `OLLAMA_HOST` (optional) | `llama3` |
+```text
+prompts/
+├── system/base.md
+├── partials/
+│   ├── context-format.md
+│   ├── output-rules.md
+│   └── stack-hints.md
+└── tasks/
+    ├── scan.md          api-docs.md    audit.md
+    ├── readme.md        diagrams.md    changelog.md
+    ├── check.md         flows.md       version-audit.md
+    ├── review.md        stack-docs.md  refresh.md
+    └── init-agent-onboarding.md
+```
 
 ## Docs and spec
 

{codeforerunner-0.4.3 → codeforerunner-0.4.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "codeforerunner"
-version = "0.4.3"
+version = "0.4.4"
 description = "Model-agnostic repository documentation tooling (prompt-first; thin CLI)."
 readme = "README.md"
 requires-python = ">=3.11"

{codeforerunner-0.4.3 → codeforerunner-0.4.4}/src/codeforerunner/bundle.py

@@ -5,6 +5,7 @@ from pathlib import Path
 
 
 def _package_prompts() -> Path:
+    """Return the path to the bundled prompts directory inside the package."""
     return Path(__file__).parent / "prompts"
 
 

{codeforerunner-0.4.3 → codeforerunner-0.4.4}/src/codeforerunner/check.py

@@ -21,6 +21,8 @@ class Violation:
 
 @dataclass(frozen=True)
 class _Rule:
+    """Drift detection rule: pattern to match, trigger files, and violation message."""
+
     id: str
     pattern: re.Pattern
     triggers: tuple[str, ...]
@@ -124,6 +126,7 @@ _CHANGELOG_FILENAME = "CHANGELOG.md"
 
 
 def _trigger_exists(repo: Path, patterns: tuple[str, ...]) -> bool:
+    """Return True if any pattern matches an existing file in repo."""
     for pat in patterns:
         if "*" in pat:
             parent = repo / Path(pat).parent
@@ -137,6 +140,7 @@ def _trigger_exists(repo: Path, patterns: tuple[str, ...]) -> bool:
 
 
 def _scanned_docs(repo: Path) -> list[Path]:
+    """Collect README.md and all *.md files under docs/ from repo."""
     docs: list[Path] = []
     readme = repo / "README.md"
     if readme.is_file():
@@ -148,6 +152,7 @@ def _scanned_docs(repo: Path) -> list[Path]:
 
 
 def _path_ignored(repo: Path, doc: Path, ignore_patterns: tuple[str, ...]) -> bool:
+    """Return True if doc's repo-relative path matches any ignore pattern."""
     if not ignore_patterns:
         return False
     try:
@@ -158,6 +163,7 @@ def _path_ignored(repo: Path, doc: Path, ignore_patterns: tuple[str, ...]) -> bo
 
 
 def _current_version(repo: Path) -> str | None:
+    """Extract the package version from pyproject.toml, or None if absent/unparseable."""
     pyproject = repo / "pyproject.toml"
     if not pyproject.is_file():
         return None
@@ -175,6 +181,7 @@ def _check_version_drift(
     ignore_patterns: tuple[str, ...],
     enabled: set[str] | None,
 ) -> list[Violation]:
+    """Scan docs for pinned version strings that don't match pyproject.toml."""
     if enabled is not None and "RV1-version-drift" not in enabled:
         return []
     current = _current_version(repo)

{codeforerunner-0.4.3 → codeforerunner-0.4.4}/src/codeforerunner/cli.py

@@ -56,6 +56,7 @@ def cmd_doc(args: argparse.Namespace) -> int:
 
 
 def _doc_for(args: argparse.Namespace, task: str) -> int:
+    """Emit bundle for *task* by delegating to cmd_doc with a synthetic Namespace."""
     ns = argparse.Namespace(repo=getattr(args, "repo", None), task=task)
     return cmd_doc(ns)
 
@@ -113,85 +114,17 @@ def cmd_mcp_server(args: argparse.Namespace) -> int:
     return mcp_server.serve(prompts_root)
 
 
-def cmd_generate(args: argparse.Namespace) -> int:
-    """Resolve the bundle for <task> and send it to the configured provider.
-
-    With --prompt-only (or when no provider/key/Ollama is reachable), outputs
-    the assembled prompt bundle to stdout for the calling agent to process.
-    """
-    from codeforerunner import providers as _providers
-    from codeforerunner.config import load_from_repo
-
-    repo_root = Path(args.repo).resolve() if args.repo else Path.cwd()
-    cfg = load_from_repo(repo_root)
-
-    ns = argparse.Namespace(repo=getattr(args, "repo", None), task=args.task)
-
-    # --prompt-only: output the bundle and stop; the calling agent is the model.
-    if getattr(args, "prompt_only", False):
-        return cmd_doc(ns)
-
-    bundle, rc = _get_bundle(ns)
-    if rc != 0:
-        return rc
-
-
-    explicit_provider = args.provider or (cfg.provider if cfg else None)
-    provider_name = explicit_provider or "anthropic"
-    model = args.model or (cfg.model if cfg else None)
-    provider_cls = _providers.get(provider_name)
-    provider = provider_cls()
-    model = model or provider.default_model
-
-    env_var = (cfg.api_key_env.get(provider_name) if cfg else None) or provider.default_env_var
-    api_key = os.environ.get(env_var)
-    if api_key is None and provider_name != "ollama":
-        if explicit_provider is None and _providers.ollama_available():
-            provider_name = "ollama"
-            provider_cls = _providers.get("ollama")
-            provider = provider_cls()
-            if not args.model:
-                model = provider.default_model
-            print("info: no API key; falling back to Ollama (local mode)", file=sys.stderr)
-        elif explicit_provider is None:
-            # Skill-mode auto-detect: no provider configured, no Ollama — output
-            # the prompt bundle for the calling agent to process directly.
-            sys.stdout.write(bundle)
-            if sys.stdout.isatty():
-                print(
-                    "\ninfo: no provider configured and Ollama not running.\n"
-                    "      Prompt bundle written above — paste into your agent,\n"
-                    "      or run: forerunner generate --prompt-only "
-                    f"{args.task}",
-                    file=sys.stderr,
-                )
-            return 0
-        else:
-            print(f"error: missing API key; set ${env_var}", file=sys.stderr)
-            return 3
-
-    if getattr(args, "stream", False):
-        try:
-            for chunk in provider.stream(prompt=bundle, model=model, api_key=api_key):
-                sys.stdout.write(chunk)
-                sys.stdout.flush()
-        except _providers.ProviderError as e:
-            print(f"error: {provider_name} provider failed: {e}", file=sys.stderr)
-            return 4
-        sys.stdout.write("\n")
-        return 0
-
-    try:
-        result = provider.complete(prompt=bundle, model=model, api_key=api_key)
-    except _providers.ProviderError as e:
-        print(f"error: {provider_name} provider failed: {e}", file=sys.stderr)
-        return 4
-
-    sys.stdout.write(result.text.rstrip() + "\n")
-    print(
-        f"# {provider_name} {result.model} {result.usage or ''}".rstrip(),
-        file=sys.stderr,
-    )
+def cmd_refresh(args: argparse.Namespace) -> int:
+    """Emit scan + check + all doc-task bundles to stdout for a full doc refresh."""
+    tasks = ["scan", "check", "readme", "api-docs", "stack-docs",
+             "diagrams", "flows", "version-audit", "audit"]
+    for i, task in enumerate(tasks):
+        ns = argparse.Namespace(repo=getattr(args, "repo", None), task=task)
+        rc = cmd_doc(ns)
+        if rc != 0:
+            return rc
+        if i < len(tasks) - 1:
+            sys.stdout.write("\n---\n\n")
     return 0
 
 
@@ -270,18 +203,8 @@ def build_parser() -> argparse.ArgumentParser:
     )
     s_doctor.set_defaults(func=cmd_doctor)
 
-    s_gen = sub.add_parser("generate", help="resolve bundle for <task> and call the configured provider")
-    s_gen.add_argument("task", help="task basename under prompts/tasks/")
-    s_gen.add_argument("--provider", help="override config provider")
-    s_gen.add_argument("--model", help="override config model")
-    s_gen.add_argument("--stream", action="store_true", help="stream output token-by-token")
-    s_gen.add_argument(
-        "--prompt-only",
-        dest="prompt_only",
-        action="store_true",
-        help="output the assembled prompt bundle to stdout; do not call a model (skill mode)",
-    )
-    s_gen.set_defaults(func=cmd_generate)
+    s_refresh = sub.add_parser("refresh", help="output all doc-refresh bundles in sequence (scan + check + all tasks)")
+    s_refresh.set_defaults(func=cmd_refresh)
 
     from codeforerunner import installer
     installer.add_subparser(sub)