donchian-strong-regime

donchian-strong-regime is a skill for Claude Code from Superior-Trade/superior-skills. It costs 84 tokens per session (1,985 once invoked), scanned A, original, MIT.

A short-selling strategy for confirmed strong downtrends in cryptocurrency. It combines several signals—moving-average separation, ADX, and recent returns—to confirm the market regime before acting, then looks for a break below a recent price low.

In plain words
What is it for?
Use it to write or test a regime-filtered Donchian short strategy, where a Donchian level is a recent high or low used to identify breakouts. It was tested on BTC and is intended for examining breakdowns during confirmed bear markets.
Why use it?
It is designed to avoid sideways markets, where breakdown signals can quickly reverse. The confirmation rules reduce the chance of entering a short trade based on a single weak signal.

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 write or test a regime-filtered Donchian short strategy, where a Donchian level is a recent high or low used to identify breakouts. It was tested on BTC and is intended for examining breakdowns during confirmed bear markets.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/superior-trade/superior-skills/donchian-strong-regime
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 donchian-strong-regime
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 donchian-strong-regime

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/superior-trade/superior-skills/donchian-strong-regime"><img src="https://agentmods.dev/badge/skills/superior-trade/superior-skills/donchian-strong-regime.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,985 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 pass 7 Sept 2026
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 $0.00084 $0.01985
Opus 5 $0.00042 $0.00992
Sonnet 5 $0.00017 $0.00397
Haiku 4.5 $0.00008 $0.00198

Measured 13d ago against content hash f29fe40deb06, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

donchian-strong-regime 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/donchian-strong-regime/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Donchian Strong-Regime Short

Trend-breakdown short, gated by a triple-confirmed strong-bear regime. Stays out of chop entirely. Validated on BTC/USDC:USDC over 162 days (2025-11-20 → 2026-05-01).

Searchable under: trend follower, breakdown, regime-gated, donchian short, structural break.

Backtest evidence

Window Trades Win rate Profit Max DD
Full period (162d) 6 100% +6.69% 0%
First-half / strong bear (82d) 6 100% +6.69% 0%
Second-half / chop (80d) 0 0% 0%

The triple-confirmation gate produced zero trades in the rangy second half — exactly the behavior a regime gate should produce. Every fired trade in the first half captured the trailing stop for profit.

Thesis

In a confirmed strong-bear regime (ema separation, ADX, recent momentum all aligned), a close below the 24-bar low (4 days of structure) reliably continues lower. The gate prevents the strategy from firing during sideways/rangy markets where the same signal mean-reverts.

Mechanics

  • Pair: validated on BTC/USDC:USDC; expected to behave similarly on other deeply-liquid majors during their own confirmed bear regimes
  • Timeframe: 4h (entry signal); 4h trend indicators (regime gate)
  • Regime gate (ALL three required):
    • EMA50 / EMA200 - 1 < -0.06 (≥6% separation = deep structural downtrend, not a fresh cross)
    • ADX(14) > 25 (trend strength confirmed)
    • close.pct_change(30) < -0.10 (last 30 bars = ~5 days, actual downside momentum)
  • Entry (short): close < lowest_24_bar_low AND regime gate satisfied
  • Exit (any of):
    • close > highest_6_bar_high (24h ceiling break — local reversal)
    • 2 consecutive bars with RSI > 55 (sustained rebound)
    • Trailing stop fires (Phase 2 — see the dsl-exit-engine skill)
  • Stops: Phase 1 hard stop at -5%; Phase 2 trailing activates at +3%, trails 2% behind peak

Full strategy code

from freqtrade.strategy import IStrategy
import pandas as pd
import talib.abstract as ta


class DonchianStrongRegimeStrategy(IStrategy):
    INTERFACE_VERSION = 3
    timeframe = "4h"
    can_short = True

    stoploss = -0.05
    trailing_stop = True
    trailing_stop_positive = 0.02
    trailing_stop_positive_offset = 0.03
    trailing_only_offset_is_reached = True

    minimal_roi = {"0": 100.0}  # disable ROI; trailing + signal exits only
    process_only_new_candles = True
    startup_candle_count = 220
    use_exit_signal = True

    def populate_indicators(self, dataframe: pd.DataFrame, metadata: dict) -> pd.DataFrame:
        dataframe["lowest_24"] = dataframe["low"].rolling(24).min().shift(1)
        dataframe["highest_6"] = dataframe["high"].rolling(6).max().shift(1)
        dataframe["ema50"] = ta.EMA(dataframe, timeperiod=50)
        dataframe["ema200"] = ta.EMA(dataframe, timeperiod=200)
        dataframe["rsi"] = ta.RSI(dataframe, timeperiod=14)
        dataframe["adx"] = ta.ADX(dataframe, timeperiod=14)

        dataframe["ema_sep"] = (
            (dataframe["ema50"] - dataframe["ema200"]) / dataframe["ema200"]
        )
        dataframe["ret_30"] = dataframe["close"].pct_change(30)
        dataframe["regime_strong"] = (
            (dataframe["ema_sep"] < -0.06)
            & (dataframe["adx"] > 25)
            & (dataframe["ret_30"] < -0.10)
        )
        return dataframe

    def populate_entry_trend(self, dataframe: pd.DataFrame, metadata: dict) -> pd.DataFrame:
        cond = (
            (dataframe["close"] < dataframe["lowest_24"])
            & dataframe["regime_strong"]
        )
        dataframe.loc[cond, "enter_short"] = 1
        dataframe.loc[cond, "enter_tag"] = "donchian_strong_bear"
        return dataframe

    def populate_exit_trend(self, dataframe: pd.DataFrame, metadata: dict) -> pd.DataFrame:
        cond = (
            (dataframe["close"] > dataframe["highest_6"])
            | ((dataframe["rsi"] > 55) & (dataframe["rsi"].shift(1) > 55))
        )
        dataframe.loc[cond, "exit_short"] = 1
        return dataframe

Read the full file on GitHub · 160 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 · 160 lines · 84 tokens per session scan A f29fe40deb06

Subscribe to this mod's changes

donchian-strong-regime is a skill published in the GitHub repository Superior-Trade/superior-skills (209 stars, last pushed 2d ago), licensed MIT. It adds 84 tokens to every session and 1,985 once invoked, about $0.0004 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.