OpenLtm CLAUDE.md

OpenLtm CLAUDE.md is an instructions file for coding agents from RohiRIK/OpenLtm. It costs 762 tokens per session, scanned A, original, MIT.

Project instructions for OpenLTM, a Claude Code plugin that stores and retrieves long-term project knowledge in a local database. They describe when to recall past decisions, save new lessons, and verify changes.

In plain words
What is it for?
Use them when starting a non-trivial task, recording an architectural decision or problem, changing the plugin, updating its version, or running its checks.
Why use it?
They help the coding assistant remember important project context between sessions and follow the repository's required development and release process.

Instructions file

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

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 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rohirik/openltm/claude-md.svg)](https://agentmods.dev/instructions/rohirik/openltm/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rohirik/openltm/claude-md"><img src="https://agentmods.dev/badge/instructions/rohirik/openltm/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 762 This file is loaded in full into every session.
When invoked 762 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 $0.00762 $0.00762
Opus 5 $0.00381 $0.00381
Sonnet 5 $0.00152 $0.00152
Haiku 4.5 $0.00076 $0.00076

Measured 5d ago against content hash a9c06273f7e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

OpenLtm 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 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.

CLAUDE.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenLTM Plugin — Long-Term Memory for AI coding agents

This plugin provides persistent semantic memory across sessions via a local SQLite database.

Rules

The goal is automatic knowledge retrieval and capture — not a call before every sentence. Use judgment.

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

Development Workflow

Every task follows this workflow:

  1. Plan — Define requirements, check existing patterns with recall
  2. Implement — Write the code
  3. Learn — After any non-obvious decision, call learn to preserve it
  4. Simplify — Run /simplify to clean up the code
  5. Verify — Run /verify (tsc + lint + test + build)

Version Bump — MANDATORY

After EVERY fix, feature, or change that touches any file in this repo, bump the version in all of these — they must match exactly:

  • package.json
  • .claude-plugin/plugin.json
  • .claude-plugin/marketplace.jsonmetadata.version and plugins[0].version
  • each packages/*/package.json (openltm-core, adapter-opencode, adapter-pi)
  • the version badge in README.md

bun run bump <version> updates most of these; bun run verify-version is the gate and fails if any are out of sync. Run it before committing. Also confirm claude plugin validate . passes.

Why: The Claude Code plugin marketplace detects new versions via .claude-plugin/plugin.json. If it is not bumped, "Update now" does nothing. Mismatched packages/* versions break the npm publish (the workspace:*^<version> rewrite). Do not skip this even for one-line fixes.

Release & Publish

Publishing the @rohirik/* npm packages is automated and tokenless (npm OIDC trusted publishing):

Read the full file on GitHub · 55 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 · 55 lines · 762 tokens per session scan A a9c06273f7e5

Subscribe to this mod's changes

OpenLtm CLAUDE.md is an instructions file published in the GitHub repository RohiRIK/OpenLtm (26 stars, last pushed 4d ago), licensed MIT. It adds 762 tokens to every session, about $0.0038 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.