sweep

sweep is a skill for Claude Code from MangroveTechnologies/mangrove-agent. It costs 195 tokens per session (4,297 once invoked), scanned A, original, MIT.

An experiment tool for testing many trading-strategy parameter combinations and ranking their backtest results. A backtest checks how a strategy would have performed on historical market data.

In plain words
What is it for?
Use it to sweep values such as RSI windows or MACD variations across one or more datasets, then validate, launch, and review the ranked results.
Why use it?
It addresses the search problem of finding promising settings instead of testing only one configuration. The engine creates candidates from a parameter space and runs the experiment through a defined lifecycle.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to sweep values such as RSI windows or MACD variations across one or more datasets, then validate, launch, and review the ranked results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mangrovetechnologies/mangrove-agent/sweep
Install

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.

Any agent
npx skills add MangroveTechnologies/mangrove-agent --skill sweep
Clone the repo
git clone --depth 1 https://github.com/MangroveTechnologies/mangrove-agent

Made for: Claude Code.

Wrote 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.

agentmods badge for sweep

README.md
[![agentmods](https://agentmods.dev/badge/skills/mangrovetechnologies/mangrove-agent/sweep.svg)](https://agentmods.dev/skills/mangrovetechnologies/mangrove-agent/sweep)
Your own site
<a href="https://agentmods.dev/skills/mangrovetechnologies/mangrove-agent/sweep"><img src="https://agentmods.dev/badge/skills/mangrovetechnologies/mangrove-agent/sweep.svg" alt="Measured on agentmods" height="20"></a>
Per session 195 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,297 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00195 $0.04297
Opus 5 $0.00097 $0.02148
Sonnet 5 $0.00039 $0.00859
Haiku 4.5 $0.00019 $0.00430

Measured 8d ago against content hash ca6f9c852507, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sweep 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.

.claude/skills/sweep/SKILL.md · 337 lines

How it starts

The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sweep Skill

This skill exists because finding a good strategy is a search problem, not a single guess. /backtest answers "is THIS config good?" A sweep answers "across this whole parameter space, which config is best?" — you give it a strategy template plus a parameter space, and the engine generates its own candidates (grid enumeration or random/Monte-Carlo sampling), backtests each against one or more datasets, and ranks the results. You author the search space once and let the engine explore it.

A sweep is NOT "screen a list then run the survivors." It generates the candidates itself from the parameter space — you never hand it a pre-made list of strategies. (That different workflow — score a fixed shortlist with SIEVE, then backtest the keepers — is /sieve/backtest//backtest/bulk. See "How this differs from /sieve" below.)

The lifecycle is intentionally explicit — validate before launch, separate from create — so you (and Oracle) can confirm the config and its run-count before paying for the fan-out:

create ──▶ [update]* ──▶ validate ──▶ launch ──▶ (running) ──▶ completed
  draft        draft      validated    launched      │
                                                      ├─▶ pause ─▶ relaunch
                                                      └─▶ delete (cancels children)

Trigger

Activate when the user:

  • Wants to search a parameter range ("sweep RSI window 7→21", "try entry-window 8 to 20 and exit-window 20 to 40")
  • Wants the best of many variations, ranked ("try every MACD config on BTC 1h and tell me the best", "compare these across timeframes")
  • Says "run an experiment" / "do a sweep" / "hyperparameter search" / "Monte-Carlo search over the params"

Do NOT activate for:

  • A single known config the user wants evaluated → /backtest
  • Screening/ranking a FIXED set of candidate strategies they already have, without a parameter search → /sieve (then /backtest / /backtest/bulk). That is a separate workflow, not a pre-step to this one.
  • Authoring a single strategy from a loose goal → /create-strategy

Read the full file on GitHub · 337 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 8d ago First seen · 337 lines · 195 tokens per session scan A ca6f9c852507

Subscribe to this mod's changes

sweep is a skill published in the GitHub repository MangroveTechnologies/mangrove-agent (5 stars, last pushed 1mo ago), licensed MIT. It adds 195 tokens to every session and 4,297 once invoked, about $0.0010 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.

Related

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…

mission69b/t2000 · 164 tokens

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.

mission69b/t2000 · 71 tokens

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.

mission69b/t2000 · 83 tokens

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.

mission69b/t2000 · 93 tokens

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…

mission69b/t2000 · 106 tokens

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.

mission69b/t2000 · 61 tokens