rlmgrep 0.1.5__tar.gz → 0.1.7__tar.gz

{rlmgrep-0.1.5 → rlmgrep-0.1.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rlmgrep
-Version: 0.1.5
+Version: 0.1.7
 Summary: Grep-shaped CLI search powered by DSPy RLM
 Author: rlmgrep
 License: MIT
@@ -61,7 +61,6 @@ rlmgrep [options] "query" [paths...]
 
 Common options:
 
-- `-n` show line numbers (default)
 - `-C N` context lines before/after (grep-style)
 - `-A N` context lines after
 - `-B N` context lines before
@@ -71,7 +70,8 @@ Common options:
 - `--no-recursive` do not recurse directories
 - `-a`, `--text` treat binary files as text
 - `-y`, `--yes` skip file count confirmation
-- `--stdin-files` treat stdin as newline-delimited file paths
+- `--files-from-stdin` treat stdin as newline-delimited file paths (e.g., `rg -l`)
+- `--files-from-rg` alias for `--files-from-stdin`
 - `--model`, `--sub-model` override model names
 - `--api-key`, `--api-base`, `--model-type` override provider settings
 - `--max-iterations`, `--max-llm-calls` cap RLM search effort
@@ -81,19 +81,19 @@ Examples:
 
 ```sh
 # Natural-language query over a repo
-rlmgrep -n -C 2 "token parsing" rlmgrep/
+rlmgrep -n -C 2 "Where is retry/backoff configured and what are the defaults?" .
 
 # Restrict to Python files
-rlmgrep "where config is read" --type py rlmgrep/
+rlmgrep "Where do we parse JWTs and enforce expiration?" --type py .
 
 # Glob filters (repeatable or comma-separated)
-rlmgrep "error handling" -g "**/*.py" -g "**/*.md" .
+rlmgrep "How do we map external API errors into internal error codes?" -g "**/*.py" -g "**/*.ts" .
 
-# Read from stdin (only when no paths are provided)
-cat README.md | rlmgrep "install"
+# Single-file semantic question (when you already have the file)
+cat README.md | rlmgrep --answer "What is this tool for and how is it used?"
 
 # Use rg/grep to find candidate files, then rlmgrep over that list
-rg -l "token" . | rlmgrep --stdin-files --answer "what does this token control?"
+rg -l "token" . | rlmgrep --files-from-stdin --answer "What does this token control and where is it validated?"
 ```
 
 ## Input selection
@@ -118,7 +118,6 @@ rg -l "token" . | rlmgrep --stdin-files --answer "what does this token control?"
   - `1` = no matches
   - `2` = usage/config/error
 
-Agent tip: use `-n` and no context for parse-friendly output, then key off exit codes.
 
 ## Regex-style queries (best effort)
 
@@ -182,18 +181,16 @@ If more than one provider key is set and the model does not make the provider ob
 - Converted image/audio text is cached in sidecar files named `<original>.<ext>.md` next to the original file and reused on subsequent runs.
 - Use `-a/--text` to force binary files to be read as text (UTF-8 with replacement).
 
-## Agent usage notes
+## Skill (Anthropic-style)
+
+A ready-to-copy skill lives in:
+
+- `skills/rlmgrep-usage/SKILL.md`
+
+Install it by copying the folder into your agent’s skills directory (for example, `~/.claude/skills/rlmgrep-usage/`), then invoke it as `$rlmgrep-usage` in prompts. This is a lightweight, documentation-only skill meant to guide when to use rlmgrep vs `rg`/`grep`.
 
-- Prefer narrow corpora (globs/types) to reduce token usage.
-- Use `--max-llm-calls` to cap costs; combine with small `--max-iterations` for safety.
-- For reproducible parsing, use `-n` and avoid context (`-C/-A/-B`).
-  
 ## Development
 
 - Install locally: `pip install -e .` or `uv tool install .`
 - Run: `rlmgrep "query" .`
 - No test suite is configured yet.
-
-## Security
-
-Do not commit API keys. Use environment variables or `~/.rlmgrep/config.toml`.

{rlmgrep-0.1.5 → rlmgrep-0.1.7}/README.md

@@ -49,7 +49,6 @@ rlmgrep [options] "query" [paths...]
 
 Common options:
 
-- `-n` show line numbers (default)
 - `-C N` context lines before/after (grep-style)
 - `-A N` context lines after
 - `-B N` context lines before
@@ -59,7 +58,8 @@ Common options:
 - `--no-recursive` do not recurse directories
 - `-a`, `--text` treat binary files as text
 - `-y`, `--yes` skip file count confirmation
-- `--stdin-files` treat stdin as newline-delimited file paths
+- `--files-from-stdin` treat stdin as newline-delimited file paths (e.g., `rg -l`)
+- `--files-from-rg` alias for `--files-from-stdin`
 - `--model`, `--sub-model` override model names
 - `--api-key`, `--api-base`, `--model-type` override provider settings
 - `--max-iterations`, `--max-llm-calls` cap RLM search effort
@@ -69,19 +69,19 @@ Examples:
 
 ```sh
 # Natural-language query over a repo
-rlmgrep -n -C 2 "token parsing" rlmgrep/
+rlmgrep -n -C 2 "Where is retry/backoff configured and what are the defaults?" .
 
 # Restrict to Python files
-rlmgrep "where config is read" --type py rlmgrep/
+rlmgrep "Where do we parse JWTs and enforce expiration?" --type py .
 
 # Glob filters (repeatable or comma-separated)
-rlmgrep "error handling" -g "**/*.py" -g "**/*.md" .
+rlmgrep "How do we map external API errors into internal error codes?" -g "**/*.py" -g "**/*.ts" .
 
-# Read from stdin (only when no paths are provided)
-cat README.md | rlmgrep "install"
+# Single-file semantic question (when you already have the file)
+cat README.md | rlmgrep --answer "What is this tool for and how is it used?"
 
 # Use rg/grep to find candidate files, then rlmgrep over that list
-rg -l "token" . | rlmgrep --stdin-files --answer "what does this token control?"
+rg -l "token" . | rlmgrep --files-from-stdin --answer "What does this token control and where is it validated?"
 ```
 
 ## Input selection
@@ -106,7 +106,6 @@ rg -l "token" . | rlmgrep --stdin-files --answer "what does this token control?"
   - `1` = no matches
   - `2` = usage/config/error
 
-Agent tip: use `-n` and no context for parse-friendly output, then key off exit codes.
 
 ## Regex-style queries (best effort)
 
@@ -170,18 +169,16 @@ If more than one provider key is set and the model does not make the provider ob
 - Converted image/audio text is cached in sidecar files named `<original>.<ext>.md` next to the original file and reused on subsequent runs.
 - Use `-a/--text` to force binary files to be read as text (UTF-8 with replacement).
 
-## Agent usage notes
+## Skill (Anthropic-style)
+
+A ready-to-copy skill lives in:
+
+- `skills/rlmgrep-usage/SKILL.md`
+
+Install it by copying the folder into your agent’s skills directory (for example, `~/.claude/skills/rlmgrep-usage/`), then invoke it as `$rlmgrep-usage` in prompts. This is a lightweight, documentation-only skill meant to guide when to use rlmgrep vs `rg`/`grep`.
 
-- Prefer narrow corpora (globs/types) to reduce token usage.
-- Use `--max-llm-calls` to cap costs; combine with small `--max-iterations` for safety.
-- For reproducible parsing, use `-n` and avoid context (`-C/-A/-B`).
-  
 ## Development
 
 - Install locally: `pip install -e .` or `uv tool install .`
 - Run: `rlmgrep "query" .`
 - No test suite is configured yet.
-
-## Security
-
-Do not commit API keys. Use environment variables or `~/.rlmgrep/config.toml`.

{rlmgrep-0.1.5 → rlmgrep-0.1.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "rlmgrep"
-version = "0.1.5"
+version = "0.1.7"
 description = "Grep-shaped CLI search powered by DSPy RLM"
 readme = "README.md"
 requires-python = ">=3.11"

{rlmgrep-0.1.5 → rlmgrep-0.1.7}/rlmgrep/__init__.py

@@ -1,2 +1,2 @@
 __all__ = ["__version__"]
-__version__ = "0.1.5"
+__version__ = "0.1.7"

{rlmgrep-0.1.5 → rlmgrep-0.1.7}/rlmgrep/cli.py

@@ -84,10 +84,22 @@ def _parse_args(argv: list[str]) -> argparse.Namespace:
     parser.add_argument("-a", "--text", dest="binary_as_text", action="store_true", help="Search binary files as text")
     parser.add_argument("--answer", action="store_true", help="Print a narrative answer before grep output")
     parser.add_argument("-y", "--yes", action="store_true", help="Skip file count confirmation")
+    parser.add_argument(
+        "--files-from-stdin",
+        action="store_true",
+        help="Treat stdin as newline-delimited file paths (e.g., rg -l)",
+    )
+    parser.add_argument(
+        "--files-from-rg",
+        dest="stdin_files",
+        action="store_true",
+        help="Alias for --files-from-stdin",
+    )
     parser.add_argument(
         "--stdin-files",
+        dest="stdin_files",
         action="store_true",
-        help="Treat stdin as newline-delimited file paths",
+        help="Deprecated: use --files-from-stdin",
     )
 
     parser.add_argument("-g", "--glob", dest="globs", action="append", default=[], help="Include files matching glob (may repeat)")

{rlmgrep-0.1.5 → rlmgrep-0.1.7}/rlmgrep.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rlmgrep
-Version: 0.1.5
+Version: 0.1.7
 Summary: Grep-shaped CLI search powered by DSPy RLM
 Author: rlmgrep
 License: MIT
@@ -61,7 +61,6 @@ rlmgrep [options] "query" [paths...]
 
 Common options:
 
-- `-n` show line numbers (default)
 - `-C N` context lines before/after (grep-style)
 - `-A N` context lines after
 - `-B N` context lines before
@@ -71,7 +70,8 @@ Common options:
 - `--no-recursive` do not recurse directories
 - `-a`, `--text` treat binary files as text
 - `-y`, `--yes` skip file count confirmation
-- `--stdin-files` treat stdin as newline-delimited file paths
+- `--files-from-stdin` treat stdin as newline-delimited file paths (e.g., `rg -l`)
+- `--files-from-rg` alias for `--files-from-stdin`
 - `--model`, `--sub-model` override model names
 - `--api-key`, `--api-base`, `--model-type` override provider settings
 - `--max-iterations`, `--max-llm-calls` cap RLM search effort
@@ -81,19 +81,19 @@ Examples:
 
 ```sh
 # Natural-language query over a repo
-rlmgrep -n -C 2 "token parsing" rlmgrep/
+rlmgrep -n -C 2 "Where is retry/backoff configured and what are the defaults?" .
 
 # Restrict to Python files
-rlmgrep "where config is read" --type py rlmgrep/
+rlmgrep "Where do we parse JWTs and enforce expiration?" --type py .
 
 # Glob filters (repeatable or comma-separated)
-rlmgrep "error handling" -g "**/*.py" -g "**/*.md" .
+rlmgrep "How do we map external API errors into internal error codes?" -g "**/*.py" -g "**/*.ts" .
 
-# Read from stdin (only when no paths are provided)
-cat README.md | rlmgrep "install"
+# Single-file semantic question (when you already have the file)
+cat README.md | rlmgrep --answer "What is this tool for and how is it used?"
 
 # Use rg/grep to find candidate files, then rlmgrep over that list
-rg -l "token" . | rlmgrep --stdin-files --answer "what does this token control?"
+rg -l "token" . | rlmgrep --files-from-stdin --answer "What does this token control and where is it validated?"
 ```
 
 ## Input selection
@@ -118,7 +118,6 @@ rg -l "token" . | rlmgrep --stdin-files --answer "what does this token control?"
   - `1` = no matches
   - `2` = usage/config/error
 
-Agent tip: use `-n` and no context for parse-friendly output, then key off exit codes.
 
 ## Regex-style queries (best effort)
 
@@ -182,18 +181,16 @@ If more than one provider key is set and the model does not make the provider ob
 - Converted image/audio text is cached in sidecar files named `<original>.<ext>.md` next to the original file and reused on subsequent runs.
 - Use `-a/--text` to force binary files to be read as text (UTF-8 with replacement).
 
-## Agent usage notes
+## Skill (Anthropic-style)
+
+A ready-to-copy skill lives in:
+
+- `skills/rlmgrep-usage/SKILL.md`
+
+Install it by copying the folder into your agent’s skills directory (for example, `~/.claude/skills/rlmgrep-usage/`), then invoke it as `$rlmgrep-usage` in prompts. This is a lightweight, documentation-only skill meant to guide when to use rlmgrep vs `rg`/`grep`.
 
-- Prefer narrow corpora (globs/types) to reduce token usage.
-- Use `--max-llm-calls` to cap costs; combine with small `--max-iterations` for safety.
-- For reproducible parsing, use `-n` and avoid context (`-C/-A/-B`).
-  
 ## Development
 
 - Install locally: `pip install -e .` or `uv tool install .`
 - Run: `rlmgrep "query" .`
 - No test suite is configured yet.
-
-## Security
-
-Do not commit API keys. Use environment variables or `~/.rlmgrep/config.toml`.