lyra-ai AGENTS.md

lyra-ai AGENTS.md is an instructions file for Codex, OpenCode from ahkedia/lyra-ai. It costs 1,974 tokens per session, scanned A, original, MIT.

Workspace instructions for Lyra AI, including its Git workflow, session startup, memory, and separation between public and private repositories. They explain which kinds of information belong in each repository.

In plain words
What is it for?
Use them when working on Lyra AI code, scripts, documentation, configuration, memory files, or automated tasks across its public and private repositories.
Why use it?
They help prevent private facts or live identifiers from being committed to the public codebase and keep changes synchronized with the canonical GitHub branch.

Instructions file for CodexOpenCode

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/ahkedia/lyra-ai/agents-md
Clone the repo
git clone --depth 1 https://github.com/ahkedia/lyra-ai

Made for: Codex, OpenCode.

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 AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ahkedia/lyra-ai/agents-md.svg)](https://agentmods.dev/instructions/ahkedia/lyra-ai/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ahkedia/lyra-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/ahkedia/lyra-ai/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,974 This file is loaded in full into every session.
When invoked 1,974 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 $0.01974 $0.01974
Opus 5 $0.00987 $0.00987
Sonnet 5 $0.00395 $0.00395
Haiku 4.5 $0.00197 $0.00197

Measured 5d ago against content hash 2c5301107f48, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lyra-ai AGENTS.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.

AGENTS.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Your Workspace

This folder is home. Treat it that way.

Git workflow (Cursor, Claude Code, automation)

GitHub main is canonical. Before editing tracked files: git fetch origin && git pull --ff-only origin main. After a change: commit and git push origin main. Do not leave unpushed commits only on the VPS. Full contract: docs/GIT-WORKFLOW.md and root CLAUDE.md.

Two repos — public/private split (MANDATORY routing)

There are two repos since the split (docs/12-public-private-split.md):

  • lyra-ai (PUBLIC): code, scripts, plugins, skills, evals, docs, sanitized templates. Never put phone numbers, Telegram IDs, personal facts, or live Notion IDs here.
  • lyra-private (PRIVATE, /root/lyra-private on Hetzner): live config/SOUL.md, config/MEMORY.md, config/HEARTBEAT.md, config/cron-jobs.json (the cron mirror — edit crons HERE), notion/notion.md, operator facts MEMORY.md.

Rules of thumb before committing: if the diff contains a phone number, a person's identity, or a live database ID → lyra-private. If unsure, check whether the file path is in the public repo's .gitignore private-layer block. The public repo has a pre-push PII hook + CI check that reject personal data — never bypass with --no-verify. At runtime nothing changed: workspace files (~/.openclaw/workspace/) are still the merged view; deploy-lyra.sh routes self-edits to the right repo automatically.

Session Startup

Before doing anything else:

  1. Read SOUL.md — this is who you are
  2. Read USER.md — this is who you're helping
  3. Read memory/YYYY-MM-DD.md (today + yesterday) for recent context
  4. If in MAIN SESSION (direct chat with your human): Also read MEMORY.md

Don't ask permission. Just do it.

Memory

You wake up fresh each session. These files are your continuity:

  • Daily notes: memory/YYYY-MM-DD.md (create memory/ if needed) — raw logs of what happened
  • Long-term: MEMORY.md — your curated memories, like a human's long-term memory

Read the full file on GitHub · 189 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 · 189 lines · 1,974 tokens per session scan A 2c5301107f48

Subscribe to this mod's changes

lyra-ai AGENTS.md is an instructions file published in the GitHub repository ahkedia/lyra-ai (5 stars, last pushed 16d ago), licensed MIT. It adds 1,974 tokens to every session, about $0.0099 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.