lc init¶

Scaffold a new ASTRA project with agent harness integration.

Synopsis¶

lc init [OPTIONS] [DIRECTORY]

DIRECTORY defaults to . (the current directory).

What it creates¶

Inside DIRECTORY (creating it if needed):

astra.yaml                    # tiny boilerplate spec with one example output
AGENTS.md                     # harness-neutral project doc (all harnesses)
CLAUDE.md                     # lightweight shim pointing to AGENTS.md (Claude harness only)
.gitignore                    # Python + lightcone state
.lightcone/
  lightcone.yaml              # currently a stub: { target: local }
results/                      # placeholder; populated by `lc run`
universes/                    # placeholder; populate via `astra universe generate -n …`
.claude/                      # Claude Code plugin (when harness is 'claude')
  skills/, agents/, scripts/, templates/
  settings.json               # the chosen permission tier
.venv/                        # Python venv (skipped with --no-venv)

lc init refuses to run if DIRECTORY/astra.yaml already exists.

Options¶

Option	Default	Effect
`--no-git`	off	Skip `git init`.
`--no-venv`	off	Skip `python -m venv .venv`.
`--harness {claude}`	prompted	AI coding harness to install skills for.
`--permissions {yolo,recommended,minimal}`	`recommended`	Which `.claude/settings.json` permission tier to install (Claude harness only).

The historical --target, --existing-project, and --sub-analysis flags have been removed. For migrating an existing project, run lc init in a fresh directory and use the /lc-from-code skill.

Permission tiers¶

Tier	Allowed	Denied
`yolo`	`Bash()`, `Edit`, `Read`, `Write`, `WebSearch`, `WebFetch`, `mcp__`	—
`recommended`	`Read`, `Edit`, `Write`, `Bash(*)`, `WebSearch`, `WebFetch`	Edits to `~/.ssh`, `~/.aws`, `~/.gnupg`, `/scratch`, `/pscratch`; `sudo`, `rm -rf`, `git push`.
`minimal`	`Read`	Everything else.

The tiers are defined as PERMISSION_TIERS in src/lightcone/cli/commands.py — adjust there if you want to add a tier or change defaults.

Examples¶

lc init                                     # scaffold in cwd; prompts for harness
lc init my-analysis --harness claude        # scaffold with Claude Code
lc init my-analysis --no-git --no-venv      # bare bones
lc init . --harness claude --permissions yolo  # for autonomous loops you trust

Next steps¶

cd my-analysis
claude           # open Claude Code
# Inside Claude Code:
/lc-new  # scope a research question into astra.yaml
# Then ask the agent to implement the spec.
# It will run lc run, watch lc status, then validate and verify.