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 skills add MangroveTechnologies/mangrove-agent --skill sweepsgit 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/sweeps)<a href="https://agentmods.dev/skills/mangrovetechnologies/mangrove-agent/sweeps"><img src="https://agentmods.dev/badge/skills/mangrovetechnologies/mangrove-agent/sweeps/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mangrovetechnologies/mangrove-agent/sweeps"><img src="https://agentmods.dev/badge/skills/mangrovetechnologies/mangrove-agent/sweeps.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00090 | $0.02726 |
| Opus 5.5 | $0.00036 | $0.01090 |
| Sonnet 5.5 | $0.00018 | $0.00545 |
| Haiku 4.5 | $0.00009 | $0.00273 |
Grade A, and why
sweeps 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 9d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
These instructions describe MangroveAI server tools and server-owned records. Discover current tools and input schemas through MCP before calling them; report unavailable capabilities without substituting a local implementation. Local execution workflows use agent_ tools and local strategy IDs. Do not pass IDs between those stores.
The engine builds the candidates, not you
A backtest asks what one strategy did. A sweep asks what a whole space of them does. You do not write the candidates and you do not hand over a list. The engine draws each run's strategy itself according to the settings of the experiment, such as what market windows to use, what assets to test, what signals to use, what risk management parameters to test, and other various knobs and dials.
The decisions a user makes are:
- What asset(s) to choose from. Present the following options only when the person
has not already answered this:
a. doesn't matter
b. popular ones (BTC, ETH, SOL, XRP, DOGE)
c. choose myself (list them, they will be verified against our approved asset list)
If they say "all markets available in the local catalog", "everything you cover",
"doesn't matter", or equivalent, that is already an asset choice. Do not ask them
to name assets or pick from the menu again. Call
list_sweep_marketswithout anassetsfilter (while applying any regimes/timeframes they already specified), then use every returned asset with at least one matching window insize_sweepand, if later requested,create_sweep.list_sweep_marketsomittedassetsmeans every catalog asset;size_sweepdoes not infer that choice when its required asset list is omitted. - What market conditions to test. Ask only if they have not already said. Pick as
many as they like, and offer only choices the catalog returns for their selection.
Use
list_sweep_marketsto get available regimes for the selected assets. A request for "current" meansregimes=["current"]; it is already answered and needs no follow-up question. A request to use the local catalog without building windows means omitwindowsand do not callbuild_market_window. Market regimes: a. current (windows with data in the last 30 days) b. bear (falling: bear, super_bear, mega_bear) c. neutral (sideways) d. bull (rising: bull, super_bull, mega_bull) e. doesn't matter (every condition) And/or: f. a specific window and timeframe (build one from market data) - What do you want the strategies built from? Pick as many as you like.
a. specific indicators (they name them; resolve every name through the graph,
use fuzzy/semantic matching with
query_knowledge) b. specific candlestick patterns (the pattern class, same instructions as above) c. indicator types (averaging, flow, momentum, oscillator, pattern, volatility) d. mix and match (signal groups) e. I don't know what I want (the engine explores the whole library) - What do you want to try different values for? Anything not picked stays at its proven default. a. risk/reward ratio b. stop loss distance c. max risk per trade d. cooldown and circuit breakers e. advanced configuration (every execution parameter) f. nothing
- Review and launch, only if they asked to create or launch. a. name the experiment, give it a description. b. confirm the launch c. launch when confirmed
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.
- 9d ago Changed · -15 lines 4c3887965cfd
- 12d ago Changed · +74 lines · -4 tokens per session e38ae61aab7d
- 1mo ago First seen · 151 lines · 94 tokens per session scan A aecea797bf1b
sweeps is a skill published in the GitHub repository MangroveTechnologies/mangrove-agent (5 stars, last pushed 2d ago), licensed MIT. It adds 90 tokens to every session and 2,726 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-14.
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.