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/earnings-preview/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/earnings-preview)<a href="https://agentmods.dev/skills/heurist-network/heurist-finance/earnings-preview"><img src="https://agentmods.dev/badge/skills/heurist-network/heurist-finance/earnings-preview/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/earnings-preview"><img src="https://agentmods.dev/badge/skills/heurist-network/heurist-finance/earnings-preview.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 | $0.00102 | $0.02750 |
| Opus 5.5 | $0.00041 | $0.01100 |
| Sonnet 5.5 | $0.00020 | $0.00550 |
| Haiku 4.5 | $0.00010 | $0.00275 |
Grade A, and why
earnings-preview 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Earnings Preview (agent swarm)
Shared plumbing and house rules: ../_shared/analyst-core.md. Event mechanics (implied move, vol crush, post-earnings drift): ../earnings-play/SKILL.md. This skill is the orchestration layer: you are the orchestrator, subagents do the reading, and you own the verdict.
First run: META Q3 2026. The traps and rules below come from that run and are self-contained.
Budget and shape
About 10 agents and 1-2 hours of wall time. Run independent agents in one message so they run concurrently, in the foreground when your next step needs all of them. Every agent writes its full report to a scratch file (<scratchpad>/<ticker>/laneN-*.md) and returns a structured summary with a source (URL or tool call) and a date on every number. Later agents read the files, so you never paste reports between agents.
Phase 0: setup (you, about 5 minutes)
- Read
profile.md,context/latest.md,context/index.md,trading/watches/and any plan that names the ticker or its sector. Note what the user holds and which plan lines this print can trip. - Confirm the date and time of the report on the company's IR site, not an aggregator. Aggregator dates were wrong for INTC and META in this repo.
hf_tool.py quote TICKERandhf_tool.py earnings TICKERfor spot and vendor EPS history. If vendors disagree on consensus by more than 5%, Lane 1 must explain why before anyone uses a number.- Write down the company's swing factor: what the market will actually trade on. META was 2027 capex and expense language; for GOOGL it is likely Cloud growth and backlog, the capex guide, and search revenue against AI substitution. Lane 2 is built around it.
- Write a blind estimate before any lane reports. From the company's own guidance and its record against that guidance, put your number for each main line (revenue, the swing-factor line, next-quarter guide) in the scratch dir. Do not read consensus, previews or lane output first. This is the anchor the rest of the run has to argue against, not the Street.
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 · 84 lines · 102 tokens per session scan A d9849c9d6e0c
earnings-preview is a skill published in the GitHub repository heurist-network/heurist-finance (11 stars, last pushed 14d ago), licensed MIT. It adds 102 tokens to every session and 2,750 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.
earnings-preview compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| earnings-previewheurist-network/heurist-finance | Skill | 11 | 14d ago | MIT | A | 102 | 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 |