lyra-ai: Instructions file for Claude Code

CLAUDE.md

lyra-ai CLAUDE.md is an instructions file for Claude Code from ahkedia/lyra-ai. It costs 555 tokens per session, scanned A, original, MIT.

Project instructions for working on the Lyra AI codebase, including its Git workflow and production-server setup.

In plain words
What is it for?
They guide when to commit and push, which copy is the source of truth, and how to keep the project copies synchronized.
Why use it?
They prevent changes from being based on an outdated copy or from causing the production server, GitHub mirror, and Mac clone to diverge.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code; mentions AGENTS.md; built for openclaw.

This is ahkedia/lyra-ai's own configuration. It tells Claude Code how to work on lyra-ai 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 lyra-ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ahkedia/lyra-ai. 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/ahkedia/lyra-ai/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ahkedia/lyra-ai

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 lyra-ai CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ahkedia/lyra-ai/claude-md/github.svg)](https://agentmods.dev/instructions/ahkedia/lyra-ai/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ahkedia/lyra-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/ahkedia/lyra-ai/claude-md/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 lyra-ai CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ahkedia/lyra-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/ahkedia/lyra-ai/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 555 This file is loaded in full into every session.
When invoked 555 The same file — it is already loaded in full.
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 $0.00555 $0.00555
Opus 5 $0.00278 $0.00278
Sonnet 5 $0.00111 $0.00111
Haiku 4.5 $0.00056 $0.00056

Measured 8d ago against content hash 48139399655e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

lyra-ai 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 8d 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 · 46 lines

What it actually says

Claude Code — Lyra (lyra-ai)

Mandatory: git before/after work

Source of truth is Hetzner production (/root/lyra-ai), NOT GitHub. Lyra self-edits on the server, so the server line is always furthest ahead. GitHub origin/main is a push-mirror of Hetzner; the Mac clone is a downstream copy that pulls from GitHub.

History: the old "GitHub main is source of truth" workflow (previously documented here) caused a 3-way divergence — 260+ commits on prod never pushed, plus a stale GitHub fork. Reconciled 2026-06-20: GitHub was force-mirrored to the prod line. Don't reintroduce the "GitHub is canonical" assumption.

On Hetzner (the canonical writer) — after a logical change set:

cd /root/lyra-ai
git add -A   # or specific paths
git commit -m "describe change"
git push origin main          # keep the GitHub mirror current

On the Mac clone (downstream, read-mostly):

git fetch origin && git pull --ff-only origin main

If you must edit on the Mac, commit + push there, then git pull on Hetzner to re-integrate. Avoid two writers diverging — Hetzner is the default writer.

Full rules, VPS deploy, and safety constraints: docs/GIT-WORKFLOW.md.

If git pull --ff-only fails, reconcile with the user before proceeding (do not force-push except a deliberate Hetzner→GitHub mirror).

Project context

  • Agent instructions for the OpenClaw workspace also live in AGENTS.md (session/memory patterns for Lyra runtime).
  • Public/private split: live personal config (SOUL.md, MEMORY.md, HEARTBEAT.md, cron-jobs.json, notion/notion.md) lives in the private repo lyra-private (/root/lyra-private on Hetzner) — never in this public repo. See docs/12-public-private-split.md. Public templates: config/SOUL-template.md, config/MEMORY-template.md, config/cron-jobs.example.json.
  • Product rules: lyra-private/config/SOUL.md, lyra-private/MEMORY.md (when applicable).
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. 8d ago First seen · 46 lines · 555 tokens per session scan A 48139399655e

Subscribe to this mod's changes

lyra-ai CLAUDE.md is an instructions file published in the GitHub repository ahkedia/lyra-ai (5 stars, last pushed 20d ago), licensed MIT. It adds 555 tokens to every session, about $0.0028 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 · 5,153 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

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

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

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