lore AGENTS.md

lore AGENTS.md is an instructions file for Codex, OpenCode from jordanhindo/lore. It costs 2,407 tokens per session, scanned A, original, MIT.

A workflow guide for Lore, a local searchable store of coding-agent session transcripts. It covers the command-line tool, the server connection, the SQLite database, search, indexing, privacy, and deletion.

In plain words
What is it for?
Use it to add or change transcript search, storage adapters, privacy controls, deletion paths, command-line features, or the agent skill.
Why use it?
It explains how to make changes safely across Lore's related parts and how to verify behavior without relying on a graphical interface.

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

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 lore AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jordanhindo/lore/agents-md.svg)](https://agentmods.dev/instructions/jordanhindo/lore/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jordanhindo/lore/agents-md"><img src="https://agentmods.dev/badge/instructions/jordanhindo/lore/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,407 This file is loaded in full into every session.
When invoked 2,407 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 $0.02407 $0.02407
Opus 5 $0.01203 $0.01203
Sonnet 5 $0.00481 $0.00481
Haiku 4.5 $0.00241 $0.00241

Measured 3d ago against content hash 11e4e8d4475c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lore 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 3d 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 · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lore Agent Workflow

Lore is a local, full-fidelity, searchable memory store for agent session transcripts. Work here touches three product surfaces:

  • The TypeScript CLI and MCP server.
  • The SQLite store, adapters, search, indexing, redaction, and deletion paths.
  • The bundled agent skill under skills/lore.

Do not copy workflows from UI-heavy apps. Lore has no app frontend. Verification means CLI behavior, MCP parity, schema/write-path safety, adapter fidelity, privacy behavior, and skill behavior.

This repo follows a Matt Pocock-style agentic coding workflow. The rule is not "add ceremony." The rule is: keep the human in planning, slice work into large vertical tracer bullets, run implementation in fresh contexts, and review with fresh eyes before integration.

Workflow Levels

Use the light workflow for small work:

  • Read the relevant code/docs first.
  • Make the smallest scoped change that solves the request.
  • Run the relevant verification command.
  • Report what changed and what proved it.

Use the program workflow for large bodies of work:

  • New product surfaces such as lore:recall, lore:brief, typed cards, privacy audit, new adapters, or new retrieval flows.
  • Store, schema, search, ranking, redaction, deletion, or compatibility changes.
  • Cross-agent skill bundle changes.
  • Multi-issue work that should land as one final PR.
  • Anything where stale memory, privacy, or broken retrieval would be costly.

Do not force the program workflow onto typo fixes, tiny docs polish, simple formatting changes, or narrow bug fixes with an obvious test seam.

Program Workflow

  1. Alignment before planning. For ambiguous work, use a grill/alignment step before writing the PRD. The goal is shared design concept, not a document for its own sake. If the answer can be discovered from the codebase, discover it instead of asking Jordan.

  2. One PRD per large body of work. Write or update one PRD under docs/PRD-*.md. The PRD is the destination document: problem, solution, extensive user stories, implementation decisions, testing decisions, seams, out of scope, and notes. It should shape the whole program, not one tiny issue.

Read the full file on GitHub · 239 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. 3d ago First seen · 239 lines · 2,407 tokens per session scan A 11e4e8d4475c

Subscribe to this mod's changes

lore AGENTS.md is an instructions file published in the GitHub repository jordanhindo/lore (13 stars, last pushed 2mo ago), licensed MIT. It adds 2,407 tokens to every session, about $0.0120 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 2026-08-30.

Related

Other instructions, from other repositories

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

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

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 · 4,345 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

next.js 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