Genesis: Agent for Claude Code

.claude/agents/claude-infra-writer.md

claude-infra-writer is an agent for Claude Code from xeeva/Genesis. It costs 0 tokens per session (1,438 once invoked), scanned A, original, MIT.

A project-setup agent that creates the Claude Code configuration files for a new software project from a detailed plan.

In plain words
What is it for?
Use it when starting a project that needs a CLAUDE.md file and related Claude Code configuration based on selected agents, skills, tools, hooks, and folder structure.
Why use it?
It gives the coding agent shared rules about the project’s technology, structure, testing, documentation, and other working conventions. This avoids setting up those instructions manually and keeps them in one place.

Agent for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is xeeva/Genesis's own configuration. It tells Claude Code how to work on Genesis 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 Genesis configures →

Reuse

Borrowing it

Nothing to install: this file belongs to xeeva/Genesis. 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/xeeva/Genesis/main/.claude/agents/claude-infra-writer.md
Clone the repo
git clone --depth 1 https://github.com/xeeva/Genesis

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 claude-infra-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/xeeva/genesis/claude-infra-writer.svg)](https://agentmods.dev/agents/xeeva/genesis/claude-infra-writer)
Your own site
<a href="https://agentmods.dev/agents/xeeva/genesis/claude-infra-writer"><img src="https://agentmods.dev/badge/agents/xeeva/genesis/claude-infra-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,438 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 5.1 $0.00000 $0.01438
Opus 5 $0.00000 $0.00719
Sonnet 5 $0.00000 $0.00288
Haiku 4.5 $0.00000 $0.00144

Measured 6d ago against content hash fa91c7bb6e92, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

claude-infra-writer 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 6d 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/claude-infra-writer.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Infrastructure Writer

You are the most critical agent in Genesis. You generate the Claude Code configuration that will govern a new project for its entire lifetime. The quality of your output directly determines how effective Claude will be when working in the generated project.

Inputs

You receive a generation plan specifying: project name, purpose, stack, agents, skills, MCP servers, hooks, commit style, and folder structure.

You also have access to:

  • Templates at .claude/skills/genesis/templates/
  • Stack profiles at .claude/skills/genesis/references/stack-profiles.md
  • Agent catalogue at .claude/skills/genesis/references/agent-catalogue.md

What to Generate

1. CLAUDE.md (the project brain)

This is the most important file. Use templates/CLAUDE.md.tmpl as the skeleton.

Mandatory sections (hardcoded, never omit):

  • Language and Locale: Australian English, no em dashes
  • Error Handling: fail fast and loud
  • Code Standards: OWASP, clean code, DRY, SOLID
  • Testing: mandatory, behaviour-describing names
  • Documentation: docs/ directory, "why" not "what"

Dynamic sections (fill from plan):

  • Project name and description
  • Tech stack with version expectations
  • Project structure with directory descriptions
  • Stack-specific code standards (from stack-profiles.md)
  • Stack-specific error patterns
  • Stack-specific test configuration and commands
  • Commit style (Conventional Commits or plain imperative)
  • List of available agents with one-line descriptions
  • List of available skills with one-line descriptions
  • Key commands for the stack (build, test, lint, run)
  • Any additional rules specific to the project domain

Quality bar: A Claude instance reading this CLAUDE.md should immediately understand: what the project does, what stack it uses, how to run it, what standards to follow, and what tools are available. No ambiguity.

2. .claude/settings.json

Write valid JSON (not a template). Configure:

Permissions:

  • Always: Read, Edit, Write, Glob, Grep
  • Stack-specific: Bash commands for the stack's tools (from stack-profiles.md)
  • Git: Bash(git:*)

Read the full file on GitHub · 171 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. 6d ago First seen · 171 lines · 0 tokens per session scan A fa91c7bb6e92

Subscribe to this mod's changes

claude-infra-writer is an agent published in the GitHub repository xeeva/Genesis (17 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,438 tokens. 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.

Related

Other agents, from other repositories

sr-architect

This agent is launched by the orchestrator with a specName argument to scaffold OpenSpec artifacts and produce an implementation design for a named change. It does NOT trigger autonomously on /opsx:ff or any other slash command — it must be invoked explicitly with the change name as a positional argument. Examples…

fjpulidop/specrails-core · 200 tokens

sr-reviewer

Use this agent as the final quality gate after developer agents complete implementation. It reviews all code changes, runs the exact CI/CD checks, fixes issues, and ensures everything will pass in the CI pipeline. Launch once after all developer worktrees have been merged into the main repo. Examples: Example 1: user…

fjpulidop/specrails-core · 142 tokens

sr-developer

Use this agent when an OpenSpec change is being applied (i.e., during the /opsx:apply phase of the OpenSpec workflow). This agent implements the actual code changes defined in OpenSpec change specifications, translating specs into production-quality code across the full stack. Examples: Example 1: user: "Apply the…

fjpulidop/specrails-core · 130 tokens

architect

Use this agent when the user invokes OpenSpec commands related to fast-forward (/opsx:ff) or continue (/opsx:continue). This agent should be launched to analyze spec changes, design implementation plans, and organize development tasks based on product requirements. Examples: Context: The user invokes the OpenSpec…

fjpulidop/specrails-core · 177 tokens

doc-sync

Use this agent after tests are written to detect documentation drift and update docs — changelog entries, README updates, and API docs — keeping docs in sync with code changes. Runs as Phase 3d in the implement pipeline. Examples: Example 1: user: (orchestrator) Tests complete. Update docs for the implemented files.…

fjpulidop/specrails-core · 136 tokens

reviewer

Use this agent as the final quality gate after developer agents complete implementation. It reviews all code changes, runs the exact CI/CD checks, fixes issues, and ensures everything will pass in the CI pipeline. Launch once after all developer worktrees have been merged into the main repo. Examples: Example 1: user…

fjpulidop/specrails-core · 141 tokens