TradeMemory is a memory and audit layer for AI trading agents that records trading decisions, outcomes, and context in a tamper-evident history. It is for traders and automated trading systems that need agents to recall past decisions and document their reasoning. Catalogue add-ons provide skills, commands, MCP tools, and related workflow components for using it.
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.
git clone --depth 1 https://github.com/mnemox-ai/tradememory-protocolWrote 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/commands/mnemox-ai/tradememory-protocol/recall)<a href="https://agentmods.dev/commands/mnemox-ai/tradememory-protocol/recall"><img src="https://agentmods.dev/badge/commands/mnemox-ai/tradememory-protocol/recall.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 5.1 | $0.00009 | $0.00424 |
| Opus 5 | $0.00005 | $0.00212 |
| Sonnet 5 | $0.00002 | $0.00085 |
| Haiku 4.5 | $0.00001 | $0.00042 |
Grade A, and why
recall 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 8d 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.
What it actually says
Recall Similar Trades
Search your trading memory for past trades that match the current market context. Results are ranked by Outcome-Weighted Memory (OWM) score — winning trades in similar contexts surface first.
Workflow
Step 1: Define Query Context
If context is provided, use it. Otherwise ask:
- Symbol: What are you trading?
- Market conditions: Trending/ranging, volatility level, session
- Strategy: Which strategy are you considering?
- Timeframe: What timeframe are you analyzing?
Step 2: Execute Recall
Use the recall_memories MCP tool:
recall_memories({
query: "market context description",
memory_types: ["episodic", "semantic", "procedural"],
limit: 10
})
OWM scoring formula weights:
- P&L outcome (40%) — profitable trades score higher
- Context similarity (30%) — matching market conditions
- Recency (20%) — recent trades weighted more
- Confidence calibration (10%) — well-calibrated confidence scores weighted more
Step 3: Present Results
For each recalled trade, show:
- OWM Score — composite relevance score
- Trade summary — symbol, direction, entry/exit, P&L
- Context match — what made this trade similar
- Lesson — the reflection/takeaway from that trade
Step 4: Synthesize
After listing individual trades, provide:
- Pattern summary: What do the top results have in common?
- Win rate in similar contexts
- Average P&L in similar contexts
- Recommendation: Based on past experience, should you take this trade?
Example
User: /recall ranging market, low volatility, Asian session, XAUUSD
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.
- 8d ago First seen · 57 lines · 9 tokens per session scan A 2dfc99306427
recall is a command published in the GitHub repository mnemox-ai/tradememory-protocol (1,416 stars, last pushed 27d ago), licensed MIT. It adds 9 tokens to every session and 424 once invoked, about $0.0000 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
tax-sanity
Tax awareness sanity-check (NOT tax advice). Walks through entity tax-efficiency, deductions, growth structure, quarterly estimateds, multi-jurisdiction, retirement/long-term questions. Produces a Tax Readiness Checklist for the person's meeting with their accountant.
memory-budget
Define or review memory budgets, ownership, and key memory risks.
alpha
Scan for alpha opportunities and spawn parallel research agents.
positions
Review all open positions with parallel subagents. Decides HOLD or SELL for each position.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.