OpenLtm AGENTS.md

OpenLtm AGENTS.md is an instructions file for Codex, OpenCode from RohiRIK/OpenLtm. It costs 567 tokens per session, scanned A, original, MIT.

A set of project instructions for OpenLTM, a local memory system that stores useful coding knowledge in a SQLite database. It explains how agents should recall, save, restore, and remove that knowledge.

In plain words
What is it for?
It guides agents on when to recall or save information, how to work with the Bun runtime, and which tests and type checks to run.
Why use it?
It helps an agent recover past decisions and project context across sessions without relying only on the current conversation.

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/rohirik/openltm/agents-md
Clone the repo
git clone --depth 1 https://github.com/RohiRIK/OpenLtm

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 OpenLtm AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rohirik/openltm/agents-md.svg)](https://agentmods.dev/instructions/rohirik/openltm/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/rohirik/openltm/agents-md"><img src="https://agentmods.dev/badge/instructions/rohirik/openltm/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 567 This file is loaded in full into every session.
When invoked 567 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 $0.00567 $0.00567
Opus 5 $0.00283 $0.00283
Sonnet 5 $0.00113 $0.00113
Haiku 4.5 $0.00057 $0.00057

Measured 3d ago against content hash 38ac5ec34232, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

OpenLtm 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 · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenLTM — agent instructions

Host-agnostic guidance for any AI coding agent working in this repo (Claude Code reads CLAUDE.md; OpenCode and other tools read this file). OpenLTM gives agents persistent semantic memory across sessions via a local SQLite database.

Using memory

The memory tools are exposed over MCP as recall, learn, context, forget, relate (in Claude Code, prefixed mcp__plugin_openltm_memory__*). The goal is automatic knowledge retrieval and capture — use judgment, not a call before every sentence.

  • recall before a non-trivial task, or when the work touches past decisions or an unfamiliar area. Skip for trivial one-liners.
  • learn after discovering a non-obvious pattern, architectural decision, or gotcha worth keeping across sessions.
  • context at session start or when switching projects, to restore goals, decisions, and gotchas.

Categories: preference | architecture | gotcha | pattern | workflow | constraint. Importance 5 never decays; everything else ages out as it goes unused.

Working in this repo

  • Runtime is Bun, not npm/node. Use bun, bunx, bun test.
  • Tests + typecheck must pass: bun test && bun run typecheck.
  • Version bumps are mandatory on any change — bun run bump <version> then bun run verify-version (it gates all version sources: package.json, .claude-plugin/plugin.json, .claude-plugin/marketplace.json, every packages/*/package.json, and the README badge).
  • No secrets, no database files in commits. data/*.db* is gitignored; keep it that way.

Shipping to OpenCode

Installing OpenLTM into OpenCode (bunx @rohirik/openltm-core --opencode) does two things: registers the @rohirik/opencode-ltm plugin in opencode.json, and deploys the bundled customization (agents, skills, plugins) from the package's assets/opencode/ into the user's OpenCode config directory.

Releasing

Tag-driven and tokenless: bump versions, add a CHANGELOG.md entry, then git tag vX.Y.Z && git push origin main vX.Y.Z. The tag fires the Release and Publish workflows; npm packages publish via OIDC trusted publishing with provenance — no stored token. Full detail in CONTRIBUTING.md.

Read the full file on GitHub · 33 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 · 33 lines · 567 tokens per session scan A 38ac5ec34232

Subscribe to this mod's changes

OpenLtm AGENTS.md is an instructions file published in the GitHub repository RohiRIK/OpenLtm (26 stars, last pushed 26d ago), licensed MIT. It adds 567 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 2026-08-30.

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