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/sentiment-positioning/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/sentiment-positioning)<a href="https://agentmods.dev/skills/heurist-network/heurist-finance/sentiment-positioning"><img src="https://agentmods.dev/badge/skills/heurist-network/heurist-finance/sentiment-positioning/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/sentiment-positioning"><img src="https://agentmods.dev/badge/skills/heurist-network/heurist-finance/sentiment-positioning.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 | $0.01148 |
| Opus 5.5 | $0.00036 | $0.00459 |
| Sonnet 5.5 | $0.00018 | $0.00230 |
| Haiku 4.5 | $0.00009 | $0.00115 |
Grade A, and why
sentiment-positioning 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sentiment & Positioning
Shared plumbing and output contract: ../_shared/analyst-core.md. Two distinct objects, one skill: sentiment (what people say/feel — weak, noisy contrarian value) and positioning (what they actually hold — stronger, because unwinding it forces flow). The unifying law: crowding is a risk amplifier, not a timer. Crowded stays crowded until a catalyst forces the unwind; sentiment extremes justify sizing and structure changes, rarely standalone entries.
The indicator battery, with honest effect sizes
Pull via web (AAII, CBOE put/call, II survey, fund flows are all free/public), insider_activity, institutional_holders, equity_screen screen_name=most_shorted_stocks, VIX via ^VIX, and news flow (yahoo news_search, web) for narrative temperature.
- Insider buying clusters — the strongest item here (open-market, 3+ insiders / 90 days, CEO+CFO within 30 days is the premium version; exclude 10b5-1 plans and exercises): ~4–6% abnormal 12-month returns documented (Lakonishok & Lee; Cohen, Malloy & Pomorski's "opportunistic vs routine" split). Insider selling is noise — asymmetry is structural. Full playbook in
event-driven. - Equity-only put/call ratio (10-day MA > ~1.0): historically coincides with above-average 30-day forward returns — a panic-washout marker. Post-2020 caveat: retail options flow and hedged structures have muddied it; single-name P/C is nearly uninterpretable (synthetic longs). Weak contrarian, index-level only.
- AAII bulls or bears > 50%: documented contrarian spread of only ~2–3% with many false positives (Fisher & Statman) — bull markets stay over-loved for quarters. Extreme bearishness at index level is the more reliable side (panic is sharper than euphoria).
- Fund flows: peak retail equity inflows precede below-median 1-year returns (Frazzini & Lamont, "Dumb Money") — a valuation-of-mood indicator on quarters, useless on weeks.
- VIX regime: level + term structure. Spot > 30 with inverted VIX futures curve = stress regime where forced deleveraging dominates fundamentals; VIX < 13 for months = complacency that makes hedges cheap (buy them then, not after). More signal in the term structure flip than the level.
- Short interest: high SI is double-edged — informed shorts predict underperformance on average, but SI > ~20% float + small float = squeeze fuel (see
short-thesis). Days-to-cover contextualizes it. - Narrative temperature: news frequency and tone on a theme over time (
yahoo news_search,web) is a crude crowding proxy — when a theme dominates news flow for weeks and the marginal story adds no new facts, the marginal buyer is being recruited by narrative, not information.
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 · 34 lines · 90 tokens per session scan A 19253e9f9297
sentiment-positioning is a skill published in the GitHub repository heurist-network/heurist-finance (11 stars, last pushed 14d ago), licensed MIT. It adds 90 tokens to every session and 1,148 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 2026-10-24.
sentiment-positioning compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sentiment-positioningheurist-network/heurist-finance | Skill | 11 | 14d ago | MIT | A | 90 | 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 |