lavra-setup

A project setup command for detecting the technology stack, choosing review agents, and saving workflow settings.

In plain words
What is it for?
Use it to set up or reconfigure a project, enable or disable agents, and add notes that guide reviews. It saves these settings in .lavra/config/project-setup.md.
Why use it?
It removes the need to identify the stack and configure review helpers by hand.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/roberto-mello/lavra/lavra-setup
Clone the repo
git clone --depth 1 https://github.com/roberto-mello/lavra
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,946 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00015 $0.02946
Opus 5 $0.00008 $0.01473
Sonnet 5 $0.00003 $0.00589
Haiku 4.5 $0.00002 $0.00295

Measured yesterday against content hash 02ce3b9ae0c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lavra-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/lavra/commands/lavra-setup.md · 339 lines

How it starts

The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.

  • Auto-detects tech stack from config files
  • Shows default agents for that stack
  • Lets you disable specific agents
  • Optionally adds reviewer context notes
  • Saves config to .lavra/config/project-setup.md

Security Note

.lavra/config/project-setup.md committed to git, readable by all review agents. Anyone with repo write access can modify. Review context sanitized on every read -- never include secrets, credentials, or sensitive business logic.

Step 1: Check for Existing Config

cat .lavra/config/project-setup.md 2>/dev/null

If config exists, use AskUserQuestion tool:

Question: "Project config already exists (stack: [stack], agents: [list]). What would you like to do?" Options: "Reconfigure (overwrite)", "View current config", "Cancel"

  • "View current config": Display full config, then ask again.
  • "Cancel": Exit immediately.
  • "Reconfigure": Continue to Step 2.

If no config, proceed to Step 2.

Step 1.5: Codebase Analysis (Optional)

Use AskUserQuestion tool:

Question: "Run codebase analysis? (3 parallel agents, ~30s) Helps planning commands understand existing architecture." Options: "Yes, analyze codebase", "No, skip"

If "No, skip", proceed to Step 2.

If accepted, dispatch 3 agents in parallel:

  1. Stack & Integrations (70 lines max): Languages, frameworks, external services, API dependencies
  2. Architecture & Structure (70 lines max): Directory layout, patterns (MVC/MVVM/etc), data flow, entry points
  3. Conventions & Testing (60 lines max): Code style, test framework, naming patterns, CI setup
Task(repo-research-analyst, "Analyze stack and integrations: languages, frameworks, external services. Max 70 lines output.")
Task(architecture-strategist, "Analyze architecture and structure: directory layout, patterns, data flow. Max 70 lines output.")
Task(pattern-recognition-specialist, "Analyze conventions and testing: code style, test framework, naming patterns. Max 60 lines output.")

Read the full file on GitHub · 339 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 339 lines · 15 tokens per session scan A 02ce3b9ae0c9

Subscribe to this mod's changes

lavra-setup is a command published in the GitHub repository roberto-mello/lavra (50 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 2,946 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.