Borrowing it
Nothing to install: this file belongs to heurist-network/heurist-finance. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/heurist-network/heurist-finance/main/.claude/skills/momentum-trend/SKILL.mdgit clone --depth 1 https://github.com/heurist-network/heurist-financeWrote 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/heurist-network/heurist-finance/momentum-trend)<a href="https://agentmods.dev/skills/heurist-network/heurist-finance/momentum-trend"><img src="https://agentmods.dev/badge/skills/heurist-network/heurist-finance/momentum-trend/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/heurist-network/heurist-finance/momentum-trend"><img src="https://agentmods.dev/badge/skills/heurist-network/heurist-finance/momentum-trend.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 | $0.00078 | $0.01078 |
| Opus 5.5 | $0.00031 | $0.00431 |
| Sonnet 5.5 | $0.00016 | $0.00216 |
| Haiku 4.5 | $0.00008 | $0.00108 |
Grade A, and why
momentum-trend 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.
How it starts
The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Momentum & Trend
Shared plumbing and output contract: ../_shared/analyst-core.md. Momentum is the best-documented anomaly in the cross-section (~1%/month winner-minus-loser spread at 3–12 month horizons, Jegadeesh & Titman 1993, replicated across countries and asset classes) — and it carries the worst left tail of any factor. This skill is both halves.
Measuring it right
- The signal is 12-1, not 12-0: total return over the past 12 months excluding the most recent month. The most recent ~1–4 weeks mean-reverts (Jegadeesh 1990) — chasing last week's winner is trading against the documented signal. Compute from
hf_tool.py prices SYM --period 2y --out FILE, in Python. - Two flavors, low correlation (~0.1–0.3), use both: cross-sectional (strong relative to peers/universe — rank the candidate against its sector ETF and SPY) and time-series (strong in absolute terms — is the asset above its own trend?). A stock outperforming a falling sector is a short-squeeze candidate, not a momentum long.
- 52-week-high proximity is its own signal (George & Hwang): distance from the 52-week high predicts returns via anchoring underreaction, ~0.5%/month spread. Near-high consolidation > deep-drawdown "recovery momentum."
- Trend template for staging (Minervini-style, get inputs from
yahoo technical_snapshot): price > 50d > 150d > 200d MA, 200d rising ≥ ~1 month, price ≥ 30% above 52w low and within ~25% of 52w high, relative strength vs SPY positive over 3/6/12mo. All true = Stage 2 (the only stage this skill buys). Breakouts want volume ≥ 1.5× 50d average; extension > 50% above the 200d MA is a penalty, not strength — mean-reversion risk dominates fresh-breakout economics there.
The crash half (this is what public momentum content omits)
Momentum's returns are negatively skewed and its crashes are predictable in kind: they cluster when the market rebounds sharply after a big drawdown — the short/avoided leg (junk that fell most) squeezes violently while the winners lag (Daniel & Moskowitz 2016; 1932, 2009, 2020 each erased 1–2 years of momentum gains in weeks). Decision rules:
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.
- 13d ago First seen · 32 lines · 78 tokens per session scan A 17bffa7b81fc
momentum-trend is a skill published in the GitHub repository heurist-network/heurist-finance (11 stars, last pushed 14d ago), licensed MIT. It adds 78 tokens to every session and 1,078 once invoked, about $0.0003 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 2026-10-24.
momentum-trend compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| momentum-trendheurist-network/heurist-finance | Skill | 11 | 14d ago | MIT | A | 78 | Claude Code |
| sector-rotationHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 39 | Claude Code, Codex |
| twitter-readerhimself65/finance-skills | Skill | 3.5k | 2d ago | MIT | A | 110 | Claude Code |
| strategy-pivot-designertradermonty/claude-trading-skills | Skill | 3.7k | 2d ago | MIT | A | 28 | Claude Code, Codex |
| energy-procurementhashgraph-online/awesome-codex-plugins | Skill | 1.5k | yesterday | Apache-2.0 | A | 93 | Claude Code, Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 269 | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |
| multi-expert-analyzerdigoal/blog | Skill | 8.6k | 2d ago | GPL-2.0 | A | 292 | Codex |