avvarre: Command for Claude Code

.claude/commands/avvarre-init.md

avvarre:init is a command for Claude Code from PralhadYadawad/avvarre. It costs 28 tokens per session (1,497 once invoked), scanned A, original, MIT.

A command that studies a project and creates an .avvarre directory containing project notes and task-tracking context. It adapts its setup to an existing codebase or an empty project.

In plain words
What is it for?
It helps record project structure, dependencies, conventions, entry points, configuration, and tasks before development continues.
Why use it?
It gives future work a written understanding of the repository instead of relying on repeated exploration.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is PralhadYadawad/avvarre's own configuration. It tells Claude Code how to work on avvarre itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything avvarre configures →

Reuse

Borrowing it

Nothing to install: this file belongs to PralhadYadawad/avvarre. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/PralhadYadawad/avvarre/master/.claude/commands/avvarre-init.md
Clone the repo
git clone --depth 1 https://github.com/PralhadYadawad/avvarre

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for avvarre:init

README.md
[![agentmods](https://agentmods.dev/badge/commands/pralhadyadawad/avvarre/avvarre-init/github.svg)](https://agentmods.dev/commands/pralhadyadawad/avvarre/avvarre-init)
Your own site
<a href="https://agentmods.dev/commands/pralhadyadawad/avvarre/avvarre-init"><img src="https://agentmods.dev/badge/commands/pralhadyadawad/avvarre/avvarre-init/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for avvarre:init

Your own site · 80×15
<a href="https://agentmods.dev/commands/pralhadyadawad/avvarre/avvarre-init"><img src="https://agentmods.dev/badge/commands/pralhadyadawad/avvarre/avvarre-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,497 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00028 $0.01497
Opus 5 $0.00014 $0.00749
Sonnet 5 $0.00006 $0.00299
Haiku 4.5 $0.00003 $0.00150

Measured 9d ago against content hash cc7e39063821, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

avvarre:init 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 9d ago.

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.

.claude/commands/avvarre-init.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/avvarre:init

Set up the .avvarre/ project memory directory.

Instructions

Step 0: Detect Workspace State

Check what state the workspace is in:

If .avvarre/ already exists with non-template content → "Already initialized. Run /avvarre:garden to audit context drift and stale tasks." and stop.

If the workspace has existing code (source files, configs, README) → follow the Existing Codebase path below.

If the workspace is empty or near-empty → follow the Greenfield path below.


Existing Codebase Path

Phase 1 — Explore the Workspace

Walk the project at a high level to understand it thoroughly:

  1. Directory tree — list the top 3 levels of the directory structure.
  2. Manifest files — read package.json, Cargo.toml, pyproject.toml, go.mod, or any framework-specific configs. Extract project name, description, and dependencies.
  3. README — read it for purpose, features, and setup instructions.
  4. Entry points — identify src/index.ts, main.py, app/ structure, etc.
  5. Config files — scan tsconfig.json, .eslintrc, .prettierrc, Dockerfile, docker-compose.yml, etc.
  6. Source samples — read 2–3 representative files from different layers (e.g., a controller, a model, a utility). Detect:
    • Naming conventions (camelCase, snake_case, PascalCase)
    • Import ordering patterns
    • Error handling approach
    • Comment/docstring style
    • File organization
  7. Test patterns — find where tests live, naming convention, framework used.

Build a mental model: architecture style, data flow, key components with file paths, tech stack.

Phase 2 — Scaffold

Call the scaffold_avvarre MCP tool with workspaceRoot and all detected values: projectName, description, techStack, targetAudience, keyFeatures, externalApis, and namingConventions. This creates the .avvarre/ directory structure with template files.

Phase 3 — Populate with Real Content

Overwrite each generated file by editing it directly with your file-editing tools:

Read the full file on GitHub · 137 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. 9d ago First seen · 137 lines · 28 tokens per session scan A cc7e39063821

Subscribe to this mod's changes

avvarre:init is a command published in the GitHub repository PralhadYadawad/avvarre (4 stars, last pushed 13d ago), licensed MIT. It adds 28 tokens to every session and 1,497 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 2026-08-31.