lorepack AGENTS.md

A set of contribution and agent instructions for Lorepack, a versioned system that builds reliable context packages from project documents and other files. Lorepack manages a lifecycle of building, checking, activating, comparing, and rolling back those packages.

In plain words
What is it for?
Use it when changing Lorepack, reviewing its architecture, or deciding where a feature belongs in the build, inspection, connection, deployment, or rollback process.
Why use it?
It gives contributors shared rules for keeping generated context deterministic and recoverable. It also clarifies that Lorepack is a build system, not primarily a document-search service.

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/burakdede/lorepack/agents-md
Clone the repo
git clone --depth 1 https://github.com/burakdede/lorepack

Made for: Codex, OpenCode.

Per session 3,609 This file is loaded in full into every session.
When invoked 3,609 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 $0.03609 $0.03609
Opus 5 $0.01804 $0.01804
Sonnet 5 $0.00722 $0.00722
Haiku 4.5 $0.00361 $0.00361

Measured yesterday against content hash d6341d051107, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lorepack 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 yesterday.

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 · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lorepack: agent and contributor rules

Read this before starting any work. It applies to every coding agent and human contributor.

1. What Lorepack is (and is not)

Lorepack is a versioned context build system for AI: "Git and Terraform for the context your AI depends on."

It compiles a directory of documents, spreadsheets and project artifacts into an immutable build that can be inspected, diffed, deployed, activated and rolled back, then read by models through MCP, HTTP or a bounded export.

It is not another local RAG server or MCP document-search tool. Retrieval is a runtime capability, not the product. If a change makes Lorepack a better search engine but a worse build system, it is the wrong change.

Non-negotiable design invariants

  1. The build is the source of truth. Every runtime (local or remote) is a projection of an immutable build. Source files are never the live serving database; a mutable index is never canonical.
  2. The lifecycle is the product: plan → build → validate → activate → diff → rollback. Every feature must strengthen one of: build, inspect, connect, deploy.
  3. Determinism. Identical canonical inputs produce an identical build ID on every OS and path. Timestamps, hostnames, absolute paths and physical SQLite bytes never affect identity.
  4. Immutability. A failed build or deploy can never corrupt the active version. Activation is a pointer change; rollback never recompiles.
  5. Provenance is mandatory. Every search result, context item and table row carries a SourceLocator. A result without one is a bug, not a style issue.
  6. Never invent truth. authority/status/supersedes are user-declared ranking hints. Lorepack must never claim it detected a conflict or decided which document is correct.
  7. Zero-surprise first run. No Python, Docker, compiler toolchain, native add-on, model download, API key or account. Ever. This constrains dependency choices absolutely.
  8. Structure before models. Preserve hierarchy, sheets, cell ranges and code boundaries. Flattening a spreadsheet into prose is an invalid implementation.
  9. Ports and adapters. core imports no parser, database, MCP, UI or Cloudflare code. Protocols and backends are adapters behind narrow interfaces. No dynamic plugin loader in v0.1.
  10. Read-only at the AI boundary. No model-facing tool may build, deploy, edit sources or execute shell commands.

Read the full file on GitHub · 220 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. yesterday First seen · 220 lines · 3,609 tokens per session scan A d6341d051107

Subscribe to this mod's changes

lorepack AGENTS.md is an instructions file published in the GitHub repository burakdede/lorepack (2 stars, last pushed 12d ago), licensed Apache-2.0. It adds 3,609 tokens to every session, about $0.0180 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.