# llm-coding-agent 0.1a0 > Source: > Published: 2026-07-02 19:33:12+00:00 **Release:** [llm-coding-agent 0.1a0](https://github.com/simonw/llm-coding-agent/releases/tag/0.1a0) Another Fable 5 experiment. Now that my [LLM library](https://llm.datasette.io/) has evolved into more of an agent framework it's time to see what a simple coding agent would look like built on it. I started a [new Python library](https://github.com/simonw/llm-coding-agent/tree/2466fa03ba8e5122c3bfa93d52167d33bce40ac6) using my [python-lib-template-repository](https://github.com/simonw/python-lib-template-repository) GitHub template repository, then ran these two prompts (here's the [Claude Code for web transcript](https://claude.ai/code/session_01TEUBvBbMipbFSoqjMiJ7ha)): `Write a spec.md for this project - it will depend on the latest “llm” alpha from PyPI and implement a Claude code style coding agent complete with tools for reading and editing files and executing commands` Then: `Commit the spec, then build it using red/green TDD in a series of sensible commits (each with passing tests and updated docs) - occasionally manually test it using the OpenAI API key in your environment` Here's [the spec](https://github.com/simonw/llm-coding-agent/blob/0.1a0/spec.md), the [resulting README file](https://github.com/simonw/llm-coding-agent/blob/0.1a0/README.md), and the [sequence of commits](https://github.com/simonw/llm-coding-agent/commits/0.1a0). I've shipped a slop-alpha to PyPI, so you can run the new agent like this: ``` uvx --prerelease=allow --with llm-coding-agent llm code ``` It's pretty good for a first attempt! Here's the (Fable-authored) [README](https://github.com/simonw/llm-coding-agent/blob/0.1a0/README.md), which lists recipes like `llm code --yolo` and `llm code --allow "pytest*" --allow "git diff*"` . It also presents [a Python API](https://github.com/simonw/llm-coding-agent/blob/0.1a0/README.md#codingagent) based around a `CodingAgent(model="gpt-5.5", root="/path", approve=True).run("Fix the failing test in tests/test_parser.py")` class which I didn't ask for but I'm delighted to see implemented. Here's the suite of tools [it implemented](https://github.com/simonw/llm-coding-agent/blob/0.1a0/llm_coding_agent/tools.py#L22), listed using `uvx ... llm tools` : `CodingTools_edit_file(path: str, old_string: str, new_string: str, replace_all: bool = False) -> str` Replace an exact string in a file. old_string must match the file contents exactly (including whitespace) and must identify a unique location unless replace_all is true. Returns a diff of the change so it can be verified. `CodingTools_execute_command(command: str, timeout: int = 120) -> str` Run a shell command in the session root directory. Returns combined stdout and stderr followed by an Exit code line. timeout is in seconds (maximum 600); on timeout the whole process tree is killed. `CodingTools_list_files(pattern: str = '**/*', path: str = '.') -> str` List files matching a glob pattern, newest first. Skips hidden directories, node_modules, __pycache__ and (in a git repository) anything covered by .gitignore. Returns at most 200 paths relative to the searched directory. `CodingTools_read_file(path: str, offset: int = 0, limit: int = 2000) -> str` Read a text file, returning numbered lines like cat -n. Paths are relative to the session root. Use offset (0-based first line) and limit (max lines) to page through files too large to read in one call. `CodingTools_search_files(pattern: str, path: str = '.', glob: str = None, max_results: int = 100) -> str` Search file contents for a regular expression. Returns matches as path:line_number:line, capped at max_results. Use glob (e.g. "*.py") to restrict which files are searched. `CodingTools_write_file(path: str, content: str) -> str` Create or overwrite a file with the given content. Parent directories are created as needed. Prefer edit_file for modifying existing files. I tried it out by running `llm code --yolo` and then prompting: `mkdir /tmp/demo and then in that folder create a simple swiftui CLI app for telling the time in ascii art` Here's [the transcript](https://gist.github.com/simonw/750009007050124cd1b390cfe8488e41), in which GPT-5.5 reasoning notes that "SwiftUI isn't suitable for a true CLI" and then builds an app that outputs this on `swift run AsciiTime` : ``` █ █████ ████ █ █ ███ ██ █ █ █ ██ █ ██ █ █ █ ████ ███ █ █ █ █ █ █ █ █ █ █ █ ███ ████ ████ ███ ███ █████ ``` Tags: [projects](https://simonwillison.net/tags/projects), [ai](https://simonwillison.net/tags/ai), [generative-ai](https://simonwillison.net/tags/generative-ai), [llm](https://simonwillison.net/tags/llm), [llm-tool-use](https://simonwillison.net/tags/llm-tool-use), [coding-agents](https://simonwillison.net/tags/coding-agents), [claude-code](https://simonwillison.net/tags/claude-code), [claude-mythos-fable](https://simonwillison.net/tags/claude-mythos-fable)