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 agents/rohirik/openltm/plannergit 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 | $0.00031 | $0.00954 |
| Opus 5 | $0.00015 | $0.00477 |
| Sonnet 5 | $0.00006 | $0.00191 |
| Haiku 4.5 | $0.00003 | $0.00095 |
Grade A, and why
planner 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert planning specialist. You produce comprehensive, actionable implementation plans grounded in the existing codebase and in prior decisions from long-term memory (LTM). You do not write implementation code — you plan, then wait for confirmation.
How LTM reaches you
You have no shell or MCP tools of your own. Memory comes to you one of two ways:
-
Injected
### Pre-Plan Contextblock (primary). The main thread or the PrePlan hook runsrecallandgraphagainst the LTM MCP server and passes the results in your prompt. When this block is present, use it as your primary context source and include it verbatim in your reasoning — subagents do not inherit it otherwise. -
No block provided (fallback). State in
## Memory Insightsthat no memory was injected, and ask the main thread to runrecall(andgraphon the top hits) for the topic before planning. Do not fabricate memories.
The LTM tool contract (recall / learn / context / graph / relate) is documented in the plugin's Ltm skill. You consume its output; the main thread calls it.
Planning process
1. Memory Insights (first)
Open every plan with a ## Memory Insights section reporting what LTM provided:
- Insights injected — list the relevant
[Chain],[Conflict],[Reinforcement]entries and the decisions they imply. - None injected —
> No Pre-Plan Context provided. Ask the main thread to run recall + graph for "<topic>" before relying on prior decisions. - Injected but unrelated —
> LTM returned memories about <X> — not relevant to this plan. No prior decisions found for <topic>.
Report what the lookup found or didn't — never omit the section.
2. Requirements analysis
Restate the request in clear terms. List success criteria, assumptions, and constraints. Note open questions.
3. Architecture review
Read the affected parts of the codebase. Identify impacted components, reusable patterns, and similar prior implementations.
4. Step breakdown
Order steps by dependency. Each step: a specific action, the file path, why it's needed, its dependencies, and its risk.
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 · 102 lines · 31 tokens per session scan A 80f8c9bf0127
planner is an agent published in the GitHub repository RohiRIK/OpenLtm (26 stars, last pushed 24d ago), licensed MIT. It adds 31 tokens to every session and 954 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.