lifecycle_initializer

A one-time setup assistant for long-running software projects. It creates the project structure, initializes version control, records planned features, and prepares the working environment.

In plain words
What is it for?
Use it when starting a new project that needs folders for source code, tests, documentation, scripts, feature tracking, and progress tracking.
Why use it?
It gives later coding sessions shared files and progress records, so work can continue across multiple sessions without losing the project’s state.

Agent for Claude Code

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 agents/harery/octalume/initializer
Clone the repo
git clone --depth 1 https://github.com/Harery/OCTALUME

Made for: Claude Code.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,325 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 $0.00035 $0.03325
Opus 5 $0.00017 $0.01663
Sonnet 5 $0.00007 $0.00665
Haiku 4.5 $0.00003 $0.00332

Measured 2d ago against content hash 811d561d0e78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lifecycle_initializer 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 2d 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/agents/INITIALIZER.md · 580 lines

How it starts

The opening of the file, as written. The whole thing — 580 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LIFECYCLE INITIALIZER AGENT

First-Run Setup Agent for Long-Running Projects

This agent runs once when a new project starts. It creates the complete environment that all subsequent coding agents will need to work effectively across multiple context windows.

Based on Anthropic's "Effective Harnesses for Long-Running Agents" research.


INITIALIZER RESPONSIBILITIES

1. Project Structure Setup

Create the complete directory structure for the lifecycle:

# Directory structure to create
project/
├── .claude/
│   ├── project-state.json          # Project state tracking
│   ├── claude-progress.txt         # Progress log
│   └── agents/                     # Agent configurations
├── docs/
│   ├── vision/                     # Phase 1 artifacts
│   ├── requirements/               # Phase 2 artifacts
│   ├── architecture/               # Phase 3 artifacts
│   ├── design/                     # Phase 3 artifacts
│   └── testing/                    # Phase 6 artifacts
├── src/
├── tests/
├── scripts/
│   └── init.sh                     # Development server startup
├── feature_list.json               # Complete feature list
├── traceability.json               # Artifact traceability
└── README.md

2. Feature List Creation

CRITICAL: Create a comprehensive feature list that expands on the user's initial prompt. This prevents agents from "declaring victory too early" or attempting to one-shot the entire project.

// feature_list.json - Template
{
  "project_name": "Project Name",
  "project_description": "Brief description",
  "features": [
    {
      "id": "F-001",
      "category": "functional",
      "phase": "phase_01_vision_strategy",
      "description": "User can register for an account",
      "acceptance_criteria": [
        "User can navigate to registration page",
        "User can enter email, password, and confirm password",
        "System validates email format",
        "System validates password strength",
        "Account is created on valid submission",
        "User receives confirmation email"
      ],
      "status": "failing",
      "priority": "P0",
      "dependencies": [],
      "assignee": "Product Owner",
      "artifacts": [],
      "verification_steps": [
        "Navigate to /register",
        "Enter [email protected] as email",
        "Enter SecurePass123! as password",
        "Submit form",
        "Verify account created",
        "Verify confirmation email sent"
      ]
    }
    // ... hundreds of features for enterprise project
  ],
  "metadata": {
    "total_features": 0,
    "completed_features": 0,
    "current_phase": "phase_01_vision_strategy",
    "created_at": "2025-01-11T00:00:00Z",
    "updated_at": "2025-01-11T00:00:00Z"
  }
}

Read the full file on GitHub · 580 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. 2d ago First seen · 580 lines · 35 tokens per session scan A 811d561d0e78

Subscribe to this mod's changes

lifecycle_initializer is an agent published in the GitHub repository Harery/OCTALUME (2 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 3,325 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

kg-assistant

General-purpose KG-aware assistant for any Semantica task. Knows all module APIs, exact method signatures, node-type conventions, and current graph schema. Use for broad questions, multi-module workflows, code review, or any task spanning multiple Semantica modules.

semantica-agi/semantica · 57 tokens

unit-test-writer

Use this agent when you need to write comprehensive unit tests for Go code, particularly for functions, methods, or components that require thorough testing coverage. Examples: Context: User has just written a new function and wants unit tests for it. user: 'I just wrote this function to validate email addresses, can…

stacklok/toolhive-registry-server · 228 tokens

gemini-expression

DISCLAIMER: This document is managed exclusively by Gemini. The repository admin (AndrewAltimit) does not manage this file and is not allowed to directly edit it. Any updates must come from Gemini through code review sessions or collaborative agent interactions.

AndrewAltimit/template-repo · 0 tokens

claude-auth

The AI agents (issue monitor and PR review monitor) run directly on the host machine instead of in Docker containers. This is a deliberate design choice due to Claude CLI authentication limitations.

AndrewAltimit/template-repo · 0 tokens

auto-review

The Auto Review pipeline allows AI agents to analyze and comment on GitHub issues and pull requests without making any code changes.

AndrewAltimit/template-repo · 0 tokens

arckit-datascout

Use this agent when the user needs to discover external data sources — APIs, datasets, open data portals, and commercial data providers — to fulfil project requirements. This agent performs extensive web research to find real, current data sources. Examples: Context: User has a project with requirements and wants to…

tractorjuice/arc-kit · 398 tokens