dca-weekly

dca-weekly is a skill for Claude Code from Superior-Trade/superior-skills. It costs 63 tokens per session (2,079 once invoked), scanned A, original, MIT.

A scheduled cryptocurrency buying strategy that adds the same amount to one open position at regular calendar intervals. This is dollar-cost averaging, or DCA: buying repeatedly over time instead of trying to choose one ideal entry price.

In plain words
What is it for?
Use it to configure, validate, or troubleshoot weekly, daily, or monthly accumulation on Superior Trade. It supports one initial buy followed by repeated additions to the same pair, with exits set according to the user’s plan.
Why use it?
It removes the need to decide when to make every purchase based on short-term price movements. The strategy keeps the additions in one trade and leaves the exit decision to the user.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the superior-skills plugin — 31 skills shipped together

Good fit Use it to configure, validate, or troubleshoot weekly, daily, or monthly accumulation on Superior Trade. It supports one initial buy followed by repeated additions to the same pair, with exits set according to the user’s plan.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/superior-trade/superior-skills/dca-weekly
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 Superior-Trade/superior-skills --skill dca-weekly
Clone the repo
git clone --depth 1 https://github.com/Superior-Trade/superior-skills

Made for: Claude Code.

Or install superior-skills, the plugin that ships this one along with the rest of its 31 skills.

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 dca-weekly

README.md
[![agentmods](https://agentmods.dev/badge/skills/superior-trade/superior-skills/dca-weekly/github.svg)](https://agentmods.dev/skills/superior-trade/superior-skills/dca-weekly)
Your own site
<a href="https://agentmods.dev/skills/superior-trade/superior-skills/dca-weekly"><img src="https://agentmods.dev/badge/skills/superior-trade/superior-skills/dca-weekly/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.

agentmods 80×15 button for dca-weekly

Your own site · 80×15
<a href="https://agentmods.dev/skills/superior-trade/superior-skills/dca-weekly"><img src="https://agentmods.dev/badge/skills/superior-trade/superior-skills/dca-weekly.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,079 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Rogue Agent · line 148
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
How audits are shown
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 $0.00063 $0.02079
Opus 5 $0.00032 $0.01040
Sonnet 5 $0.00013 $0.00416
Haiku 4.5 $0.00006 $0.00208

Measured 13d ago against content hash 7939b63498a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

dca-weekly 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 13d 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.

skills/dca-weekly/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Strategy: DCA · Scheduled Buys

When to use

A user asks to "buy X every week", "DCA into BTC", "scheduled buy", "accumulator", "monthly buy", or any variation that means open a position once, then keep adding to it on a calendar cadence. Not for "buy when price drops" — that's grid trading (see grid-trading).

What it does

  • Holds one open trade per pair (Freqtrade's hard rule).
  • The first calendar trigger opens the trade with a small initial stake.
  • Every subsequent trigger calls adjust_trade_position and adds the same notional to the open trade.
  • The position grows in fills inside a single Trade row. PnL is reported per-trade.
  • Exits only when the user sets one (typically never, for true DCA — stoploss = -0.99 and no populate_exit_trend).

Backtest reference

Window BTC/USDC 1d, 2025-11-15 → 2026-05-01 (auto-narrowed to data availability, ~10 weeks)
Trades 1 (still open at end, force-closed)
Entry orders inside the trade 10 (1 initial + 9 weekly DCA, tagged weekly_dca)
Stake per buy ~$36.87
Total invested ~$365 of $10,000 wallet
Per-trade PnL +10.0%
Wallet PnL +0.37% / +$36.61
Holding 66 days
Backtest ID 01kqyz1ysdy9dyw7tbdrhz5gek

The (rejected_signals: 9) warning in logs is normal: populate_entry_trend keeps emitting Monday flags even while a trade is open, but adjust_trade_position does the actual buys.

The Freqtrade primitives that make this work

These four flags are the difference between v1 (1 trade ever, the rest rejected) and v2 (a real ladder of fills). All four are required:

position_adjustment_enable = True
max_entry_position_adjustment = 26   # cap on number of weekly adds
max_dca_multiplier = 27.0            # 1 initial + 26 adds

Plus two callbacks:

  • custom_stake_amount — divides the user-configured stake by max_dca_multiplier so the initial entry leaves room for the future weekly adds.
  • adjust_trade_position — the calendar trigger. Returns (stake, tag) to add, None to do nothing.

Read the full file on GitHub · 157 lines

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. 13d ago First seen · 157 lines · 63 tokens per session scan A 7939b63498a9

Subscribe to this mod's changes

dca-weekly is a skill published in the GitHub repository Superior-Trade/superior-skills (209 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 2,079 once invoked, about $0.0003 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.