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.
npx agentmods add instructions/rohirik/openltm/claude-mdgit clone --depth 1 https://github.com/RohiRIK/OpenLtmWrote 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.
[](https://agentmods.dev/instructions/rohirik/openltm/claude-md)<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>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.
| Model | Per session | Once 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 |
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.
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.
- Call
recallbefore a non-trivial task, or when the work touches past decisions or an unfamiliar area. Skip it for trivial one-liners. - Call
learnafter discovering a non-obvious pattern, architectural decision, or gotcha worth keeping across sessions. - Call
contextat session start or when switching projects, to restore goals, decisions, and gotchas.
Development Workflow
Every task follows this workflow:
- Plan — Define requirements, check existing patterns with
recall - Implement — Write the code
- Learn — After any non-obvious decision, call
learnto preserve it - Simplify — Run
/simplifyto clean up the code - 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.json→metadata.versionandplugins[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):
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.
- 5d ago First seen · 55 lines · 762 tokens per session scan A a9c06273f7e5
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.
Other instructions, from other repositories
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).