Shapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.
The English summary is being prepared. Showing the original description.
Scaffolds new projects with git, CI/CD workflows, pre-commit hooks, and build config. Use when starting a new Python, Rust, or TypeScript project from scratch.
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Interactive workflow for initializing new software projects with complete development infrastructure.
Load modules/language-detection.md
Load modules/metadata-collection.md
Gather:
Check for existing configurations:
ls -la
Verification: Run the command with --help flag to verify availability.
If files exist (Makefile, .gitignore, etc.):
Load modules/template-rendering.md
Run initialization script:
python3 plugins/attune/scripts/attune_init.py \
--lang {{LANGUAGE}} \
--name {{PROJECT_NAME}} \
--author {{AUTHOR}} \
--email {{EMAIL}} \
--python-version {{PYTHON_VERSION}} \
--description {{DESCRIPTION}} \
--path .
Verification: Run the command with --help flag to verify availability.
The script also scaffolds the project decision journal: docs/tradeoffs.md
and docs/lessons-learned.md. These are append-only logs that later workflows
(brainstorm, specify, plan, execute, review) write to as decisions and lessons
arise. Existing journal files are never overwritten. The format follows the
leyline:decision-journal contract; init uses leyline's template when present
and a vendored copy otherwise, so it works with or without leyline installed.
Verification: Confirm docs/tradeoffs.md and docs/lessons-learned.md
exist and each contains an ## Active index and an ## Archive section.
# Check if git is initialized
if [ ! -d .git ]; then
git init
echo "Git repository initialized"
fi
Verification: Run git status to confirm working tree state.
Validate setup:
# Check Makefile targets
make help
# List created files
git status
Verification: Run git status to confirm working tree state.
Advise user to:
# Install dependencies and hooks
make dev-setup
# Run tests to verify setup
make test
# See all available commands
make help
Verification: Run pytest -v to verify tests pass.
--langchmod +x on scriptsmake help shows available targetsmake test runs without errors (even if no tests yet)docs/tradeoffs.md and docs/lessons-learned.md exist, each with an
## Active index and an ## Archive section.--no-git) and make help lists targets.--dry-run writes no files, including the journal.**Verification:** Run `pytest -v` to verify tests pass.
User: /attune:project-init
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Shapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.
The English summary is being prepared. Showing the original description.
Inverts burden of proof for code additions. Use when reviewing PRs, planning refactors, or running unbloat to challenge every addition's necessity.
The English summary is being prepared. Showing the original description.
Tracks per-agent token usage and flags waste in parallel dispatch. Use when evaluating parallel agent efficiency or after a multi-agent run.
The English summary is being prepared. Showing the original description.
Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.
The English summary is being prepared. Showing the original description.
Evaluates API surface design, consistency, and exemplar alignment. Use when reviewing public API changes or before releasing a new API surface.
The English summary is being prepared. Showing the original description.
Selects architecture paradigm via research before scaffolding. Use when architecture is undecided and the choice needs justification and documentation.
The English summary is being prepared. Showing the original description.