llm-init CLAUDE.md

llm-init CLAUDE.md is an instructions file for coding agents from ashtonian/llm-init. It costs 941 tokens per session, scanned A, original, MIT.

A project instruction file for Claude Code that defines work modes, such as parallel, interactive, quick, and idea-pipeline workflows.

In plain words
What is it for?
Use it to control execution style for multi-step development, complex decisions, small fixes, and projects started from scratch.
Why use it?
It gives the coding agent consistent rules for choosing how to handle different kinds of tasks and when to involve the user.

Instructions file

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 instructions/ashtonian/llm-init/claude-md
Clone the repo
git clone --depth 1 https://github.com/ashtonian/llm-init

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 llm-init CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ashtonian/llm-init/claude-md.svg)](https://agentmods.dev/instructions/ashtonian/llm-init/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ashtonian/llm-init/claude-md"><img src="https://agentmods.dev/badge/instructions/ashtonian/llm-init/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 941 This file is loaded in full into every session.
When invoked 941 The same file — it is already loaded in full.
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 $0.00941 $0.00941
Opus 5 $0.00470 $0.00470
Sonnet 5 $0.00188 $0.00188
Haiku 4.5 $0.00094 $0.00094

Measured 5d ago against content hash b7a732834b39, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

llm-init CLAUDE.md 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 5d 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.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Instructions for test-project

Execution Modes

Mode When How
Parallel (default) Multi-step features, build work, any task with 2+ independent subtasks Decompose → task files → launch agents
Interactive Complex decisions, ambiguous requirements, user wants to pair, initial project setup Plan file workflow, step-by-step with user
Quick Trivial fixes, one-liners, small edits Just do it — no plans or tasks needed
Idea Pipeline Starting from scratch, 0→100 Interactive for Research/Spec/Plan, then Parallel for Build

Mode Keywords

To activate... User says...
Parallel (default) Any multi-step request, or: "go parallel", "fan out", "batch it", "go wild"
Interactive "interactive", "walk me through", "step by step", "let's think about", "guide me", "let's pair"
Quick "just do it", "quick fix", "small change", "one-liner", "trivial"
Idea Pipeline "I have an idea", "start from scratch", "build me a...", "0 to 100"
Shelve "shelve", "save state", "checkpoint", "pause this", "save progress"

Auto-Escalation to Interactive

Switch from Parallel to Interactive automatically when:

  • Requirements are ambiguous and can't be clarified from specs
  • Cannot decompose into 2+ independent subtasks
  • Irreversible external actions needed (deployments, migrations)
  • User expresses uncertainty ("I'm not sure", "what do you think")
  • Brand-new project with empty AGENT_GUIDE.md (use Interactive for initial setup)

Custom Commands

Command What It Does
/decompose Break a request into parallel tasks (75-150 turns each)
/new-task Create a single task file in the backlog
/status Task queue dashboard with analysis
/launch Pre-flight checks + launch parallel agents
/plan Select and create the right plan template
/review Run quality gates and review current work
/shelve Checkpoint work with structured handoff
/requirements Iterative requirement gathering → package spec
/architecture-review Assess decisions, tradeoffs, edge cases
/adr Create an Architecture Decision Record
/security-review Security assessment of codebase or feature
/prd Interactive PRD → sized task files in backlog
/release Release preparation with checklist and changelog

Read the full file on GitHub · 72 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. 5d ago First seen · 72 lines · 941 tokens per session scan A b7a732834b39

Subscribe to this mod's changes

llm-init CLAUDE.md is an instructions file published in the GitHub repository ashtonian/llm-init (2 stars, last pushed 7mo ago), licensed MIT. It adds 941 tokens to every session, about $0.0047 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens