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 commands/rohirik/openltm/memorygit clone --depth 1 https://github.com/RohiRIK/OpenLtmWhat 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 | $0.00041 | $0.01350 |
| Opus 5 | $0.00020 | $0.00675 |
| Sonnet 5 | $0.00008 | $0.00270 |
| Haiku 4.5 | $0.00004 | $0.00135 |
Grade A, and why
memory 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 2d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parse the first word of the arguments as <subcommand>. Pass remaining words as <args>.
If no subcommand given, show:
Usage: /openltm:memory <subcommand>
recall — search memories
/openltm:memory recall [query] [--category X] [--project X] [--limit N]
learn — store insight
/openltm:memory learn [insight] [--category X] [--importance N] [--save-context]
forget — delete memory by ID
/openltm:memory forget <id> [reason]
relate — link two memories
/openltm:memory relate <src-id> <tgt-id> <type>
propose — review pending memory proposals from EvaluateSession
/openltm:memory propose — list all pending proposals
/openltm:memory propose review — show proposals interactively
/openltm:memory propose accept <session-id> <index>
/openltm:memory propose reject <session-id> <index>
recall
Search LTM memories. Call mcp__plugin_openltm_memory__recall with parsed args:
| Arg | Field |
|---|---|
| positional text | query |
--category X |
category |
--project X |
project |
--limit N |
limit (default 10) |
Display each result: ID · content · category · importance ★ · confirmed count · tags · relations.
FTS5 supports AND, OR, NOT, phrase matching ("bun sqlite"). Results ranked: relevance → importance → confidence.
learn
Store a memory via mcp__plugin_openltm_memory__learn. Parse args:
| Arg | Field | Default |
|---|---|---|
| positional text | content |
required |
--category X |
category |
pattern |
--importance N |
importance |
3 |
--project X |
project_scope |
current project |
--tags t1,t2 |
tags |
— |
--save-context |
also write to context_items |
off |
If no args given, review the session for extractable insights. Extract each, classify, then call learn for each.
Dedup: calling with identical content reinforces — never creates duplicates.
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.
- 2d ago First seen · 161 lines · 41 tokens per session scan A 6024f08f8831
memory is a command published in the GitHub repository RohiRIK/OpenLtm (26 stars, last pushed 24d ago), licensed MIT. It adds 41 tokens to every session and 1,350 once invoked, about $0.0002 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 commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
component
Scaffold a new React component grounded in the paper-mono primitives. Requires explicit kind or a nearest-existing-component match. No empty divs, no speculative scaffolding.
memory-store
Store an insight, decision, or pattern to memory.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
no-vibe
Enter no-vibe mode in OpenCode (tutor mode, no direct project file writes).
teach-me-testing
Teach testing progressively through structured sessions. Use when user says ""lets learn testing"" or ""I want to study test practices"".