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 skills/mangrovetechnologies/mangrove-agent/create-strategynpx skills add MangroveTechnologies/mangrove-agent --skill create-strategygit clone --depth 1 https://github.com/MangroveTechnologies/mangrove-agentWrote 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/skills/mangrovetechnologies/mangrove-agent/create-strategy)<a href="https://agentmods.dev/skills/mangrovetechnologies/mangrove-agent/create-strategy"><img src="https://agentmods.dev/badge/skills/mangrovetechnologies/mangrove-agent/create-strategy.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 | $0.00140 | $0.03138 |
| Opus 5 | $0.00070 | $0.01569 |
| Sonnet 5 | $0.00028 | $0.00628 |
| Haiku 4.5 | $0.00014 | $0.00314 |
Grade A, and why
create-strategy 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 6d 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Strategy Skill
The agent's job in this skill: turn a loose user goal ("momentum on ETH") into a strategy config with specific signals and specific parameters backed by evidence, not library defaults.
Two mechanisms drive "intuition":
- Mechanism 2 (reference strategies) — the primary path. Curated known-good configs. The agent searches these FIRST, bulk-backtests the top matches onto the user's target, and promotes by ranked performance. Zero parameter guessing for the common case.
- Mechanism 1 (KB-grounded parameters) — the fallback. When
references don't fit (unusual asset, unusual goal, or user wants to
modify), the agent is REQUIRED to call
kb_searchfor every signal it picks before finalizing params. No library-default fallback.
Portability — reference strategies are signal combos, not pins
Every reference in the library is a portable signal combination: the
asset and timeframe on the reference record are where Oracle found
the combo worked, not a constraint on where you can apply it.
build_strategy_from_reference accepts both asset and timeframe
overrides for exactly this reason. If the user asks for a strategy on
AVAX 1h and search returns references recorded on BTC 1h + SOL 5m,
both are valid candidates — retarget them onto (AVAX, 1h) and let the
backtest pick the winner. Never quote the reference's own stored
metrics to the user as if they apply to the retarget.
Bulk-backtest is the default
When Phase A returns multiple plausible matches (the common case), do not ask the user to pick by label or description — build all of them onto the user's (asset, timeframe), backtest each, and rank by actual performance. Picking by label is a KB-grounding regression; the whole point of the library is measured outcomes. Ask the user to choose only when the backtests tie, or to pick between equivalent PASSes.
A third mechanism (mined parameter priors from the 1.4M-strategy DB) will land via MangroveAI endpoint after MangroveOracle issue #156. This skill will transparently benefit once the SDK exposes it — no rewrite needed here.
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.
- 6d ago First seen · 236 lines · 140 tokens per session scan A 053ae6eb0b0c
create-strategy is a skill published in the GitHub repository MangroveTechnologies/mangrove-agent (5 stars, last pushed 1mo ago), licensed MIT. It adds 140 tokens to every session and 3,138 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
t2000-job
Escrow USDC for agent-to-agent deliverable work (A2A jobs). Use when hiring another agent for async work (research reports, builds, SLA tasks) or when selling deliverable work yourself (list a service: fixed price + SLA, no server needed), or posting/claiming open jobs on the board (t2 job open / claim) — anything…
t2000-receive
Generate a payment request for the t2000 Agent Wallet — print the wallet address, an ANSI QR code, and (via MCP) a Payment Kit URI (sui:pay?…). Use when asked to receive a payment, share a wallet address, create a payment link, or set up a fund-me link.
t2000-send
Send USDC, USDsui, or SUI from the t2000 Agent Wallet to another Sui address. Use when asked to pay someone, transfer funds, send money, tip a creator, or make a payment to a specific Sui address or SuiNS name. Do NOT use for API payments — use the t2000-pay skill for x402-protected services.
t2000-swap
Swap tokens on Sui via Cetus Aggregator (20+ DEXs, best-route across SUI, USDC, USDsui, USDT, USDe, ETH, GOLD, NAVX, WAL, vSUI, and more). Use when asked to swap, trade, convert, exchange, or "turn X into Y". Do not use for sending — use the t2000-send skill for transfers.
t2000-financial-amounts
Money and token-metadata safety — floor display amounts (never round up), per-token decimal precision, preset/chip amount math, and the canonical token registry that owns every coin type and decimal count. Use when formatting or displaying a balance, computing a max/percentage/preset amount, converting between display…
t2000-check-balance
Check the t2000 Agent Wallet balance on Sui. Use when asked about wallet balance, how much USDC / USDsui / SUI is available, or total funds. Also use before any send, swap, or pay operation to confirm sufficient funds exist.