llm-tools-todo
LLM plugin providing session-based todo management tools for Simon Willison's llm, a la Claude Code.
Installation
Install this plugin in the same environment as LLM. You'll need at least LLM 0.26a1 or later.
From PyPI (recommended)
llm install llm-tools-todo
From source
git clone https://github.com/dannyob/llm-tools-todo
cd llm-tools-todo
llm install .
Usage
The plugin provides a single Todo toolbox with six todo management operations:
Available Tools
begin- Start a new todo sessionend- End current session and cleanuplist- Display all todos in current sessionwrite- Replace entire todo listadd- Add new todo itemscomplete- Mark todos as completed
Basic Usage
# Start a new todo session
llm prompt -m gpt-4o-mini "Please start a new todo session" --tool Todo
# Add some tasks
llm -c prompt -m gpt-4o-mini "Add tasks: review code, run tests, update docs" --tool Todo
# Mark tasks complete
llm -c prompt -m gpt-4o-mini "Mark the first task as completed" --tool Todo
Session Management
Each todo session gets a unique identifier and stores data in temporary files. Sessions are automatically managed:
- Session files stored as
/tmp/llm-todos-{session_id}.json - Data persists until session is ended with
end - Multiple concurrent sessions supported
Todo Item Structure
Each todo item includes:
- Unique ID
- Content description
- Status (pending/in_progress/completed)
- Priority (high/medium/low)
- Created and updated timestamps
Development
Setup Development Environment
# Clone and set up development environment
git clone https://github.com/dannyob/llm-tools-todo
cd llm-tools-todo
make dev-setup
source .venv/bin/activate
Testing
make test # Run all tests
make test-coverage # Run tests with coverage report
make quick-test # Fast test run (exits on first failure)
Plugin Testing
After installation, verify the plugin is working:
llm tools
# above should show Todo tools listed
llm prompt "Please start a new todo session" --tool Todo
llm prompt -c "Add a single Todo, saying 'check todo list works'" --tool Todo
llm prompt -c "What is in my todo list?" --tool Todo
llm prompt -c "Mark the check todo item as done" --tool Todo
llm prompt -c "Now end the Todo list" --tool Todo
Credits and Thanks
Inspired by Claude Code's simple Todo functionality, and Joe
Haddad's claude-todo-emulator.
Coded with Claude.
Metadata
Release files for llm-tools-todo 0.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| llm_tools_todo-0.3.tar.gz | 14.1 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| llm_tools_todo-0.3-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 25.5 kB
Release files / llm_tools_todo-0.3.tar.gz
| Download URL | llm_tools_todo-0.3.tar.gz |
|---|---|
| Size | 14.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
0932e6fd9c1e480acad08c7821d26c30e544cc3bfdbb703ce38f313172234d91
|
|
BLAKE2b-256 checksum How to use checksums |
4d0eee7e35a64c8e4e38ac22946236ee397aa4ffcf6ac00401d05e8d9f38aa4a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.10
|
Release files / llm_tools_todo-0.3-py3-none-any.whl
| Download URL | llm_tools_todo-0.3-py3-none-any.whl |
|---|---|
| Size | 11.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b526236e63ab236f094a4edba84c6dbda90fb6b816aa3839966e527888c83255
|
|
BLAKE2b-256 checksum How to use checksums |
e9b99eedf5dc6c084230a4040ae1fae8170bad1dc090d38ffedf852370536876
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.10
|
Security for llm-tools-todo 0.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.