What is earnings-play?

A guide to analysing a company's upcoming or recently released earnings report. It compares the market's expected price move with the company's past earnings moves and examines the tendency for prices to drift after results.

Use it to estimate an implied move, compare it with historical earnings reactions, assess volatility changes after the report, and study post-earnings announcement drift.

The option market's expected move may differ from the company's usual reaction, and trading during the announcement can be costly. Separating the event itself from the later price drift supports a more measured hold-or-trade decision.

How heurist-network/heurist-finance configures Claude Code

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/heurist-network/heurist-finance/main/.claude/skills/earnings-play/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/heurist-network/heurist-finance

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/heurist-network/heurist-finance/earnings-play/github.svg)](https://agentmods.dev/skills/heurist-network/heurist-finance/earnings-play)

Your own site

<a href="https://agentmods.dev/skills/heurist-network/heurist-finance/earnings-play"><img src="https://agentmods.dev/badge/skills/heurist-network/heurist-finance/earnings-play/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/heurist-network/heurist-finance/earnings-play"><img src="https://agentmods.dev/badge/skills/heurist-network/heurist-finance/earnings-play.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,307 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.

Model	Per session	Once invoked
Fable 5.1	$0.00092	$0.01307
Opus 5.5	$0.00037	$0.00523
Sonnet 5.5	$0.00018	$0.00261
Haiku 4.5	$0.00009	$0.00131

Measured 13d ago against content hash 00b79a2c848d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

earnings-play 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.

.claude/skills/earnings-play/SKILL.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Earnings Play

Shared plumbing and output contract: ../_shared/analyst-core.md. Earnings is where retail loses money by trading the event and where the documented edge is in the aftermath. Keep those separate — and branch first on where the print sits (hf_tool.py earnings SYM): if it's ahead, run the implied-vs-realized workbench; if it already happened, skip straight to PEAD.

Before the print: the implied-vs-realized workbench

Get the date and the implied move. yahoo equity_overview symbol=SYM (or hf_tool.py earnings) for the earnings date; options_chain for the expiry just after it. Implied move ≈ ATM straddle price ÷ spot (use mid here; both legs). Report it as a %. If no expiry just after the event is listed yet, strip the event variance from the term structure: total ATM variance (σ²T) of the nearest expiry containing the event minus that of the last expiry before it — the difference is the event's implied variance; label the derived move as term-structure-derived.
Build the realized history — never skip this. Pull prices SYM --period 3y --out FILE, find the last 8+ earnings dates (hf_tool.py earnings SYM / equity_overview / web for the dates), and compute the actual close-to-next-open and close-to-next-close moves. The comparison of this straddle vs this stock's own history is the entire pre-event edge, and almost nobody retail computes it.
The base rate: roughly 70% of realized earnings moves come in under the implied move (CBOE/sell-side studies — cite as base rate, varies by regime and name). That's why systematically buying the pre-earnings straddle loses, and why selling it isn't free either: the 30% that exceed include the 3× overshoots that dominate expectancy. Gap risk is not diversifiable within one name.
Vol-crush mechanics: front-expiry IV typically drops 30–50% at the open after the print. Every long-options position held through earnings pays this toll — a long call can be right on direction and still lose. If the view is "big move coming," the clean expression is buying vol weeks before the event hump inflates and exiting into the print, not through it (see options-strategist).

Read the full file on GitHub · 35 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.

13d ago First seen · 35 lines · 92 tokens per session scan A 00b79a2c848d

Subscribe to this mod's changes

earnings-play is a skill published in the GitHub repository heurist-network/heurist-finance (11 stars, last pushed 14d ago), licensed MIT. It adds 92 tokens to every session and 1,307 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.

Finance and fintech ai-agents codex

earnings-play next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
earnings-playheurist-network/heurist-finance	Skill	11	14d ago	MIT	A	92	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

heurist-finance: Skill for Claude Code