trading-ops: Command for Claude Code

.claude/commands/scan-earnings.md

scan-earnings is a command for Claude Code from l3lackcurtains/trading-ops. It costs 16 tokens per session (650 once invoked), scanned A, original, MIT.

A command for checking a company’s upcoming earnings report, the scheduled update on its financial results. It applies an eight-part checklist and records what happened after the report.

In plain words
What is it for?
Use it with a stock ticker to review profit and sales growth, cash flow, margins, company guidance, investor ownership, analyst changes, options positioning, and the share-price reaction after the previous report.
Why use it?
It gathers the information needed to judge an earnings setup in the week or two before results, or to review the market’s reaction afterward. It updates only the earnings section of an existing stock scan.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is l3lackcurtains/trading-ops's own configuration. It tells Claude Code how to work on trading-ops itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything trading-ops configures →

Reuse

Borrowing it

Nothing to install: this file belongs to l3lackcurtains/trading-ops. 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/l3lackcurtains/trading-ops/main/.claude/commands/scan-earnings.md
Clone the repo
git clone --depth 1 https://github.com/l3lackcurtains/trading-ops

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.

agentmods badge for scan-earnings

README.md
[![agentmods](https://agentmods.dev/badge/commands/l3lackcurtains/trading-ops/scan-earnings/github.svg)](https://agentmods.dev/commands/l3lackcurtains/trading-ops/scan-earnings)
Your own site
<a href="https://agentmods.dev/commands/l3lackcurtains/trading-ops/scan-earnings"><img src="https://agentmods.dev/badge/commands/l3lackcurtains/trading-ops/scan-earnings/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 scan-earnings

Your own site · 80×15
<a href="https://agentmods.dev/commands/l3lackcurtains/trading-ops/scan-earnings"><img src="https://agentmods.dev/badge/commands/l3lackcurtains/trading-ops/scan-earnings.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 650 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.00650
Opus 5 $0.00008 $0.00325
Sonnet 5 $0.00003 $0.00130
Haiku 4.5 $0.00002 $0.00065

Measured 10d ago against content hash 49845f95ca26, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

scan-earnings 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 10d 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/commands/scan-earnings.md · 44 lines

What it actually says

Run an earnings-only scan for: $ARGUMENTS

Partial scan — updates only the Earnings setup section. Use during the 7–14 days before a print, or immediately post-print to record the reaction.

Protocol in guide/scan/ — see structure.md for the section format and data.md for sourcing.

Steps

  1. Verify scanned/stocks/$ARGUMENTS/current.md exists. If not, tell the user to run /scan $ARGUMENTS first.

  2. Read-before-scan per protocol.md — capture prior earnings setup notes if any (especially the 8-point checklist if it was already partly filled).

  3. Pull earnings data per data.md:

    • Finviz quote page (next earnings date, EPS estimate)
    • Seeking Alpha for transcripts, guidance, capital allocation tone (seekingalpha.com/symbol/$ARGUMENTS/earnings)
    • WebSearch for analyst-revision direction post-prior-print, whisper number, post-print 1–3 day reaction history
    • ChartExchange for max-pain magnetic interplay around the print date
  4. Run 8-point pre-print checklist:

    1. EPS ≥ 25% YoY accelerating
    2. Revenue ≥ 25% YoY 3rd consecutive quarter
    3. FCF up alongside net income
    4. Margins expanding or holding
    5. Mgmt raised guidance
    6. Inst holders increased (per Pillar 6 from prior current.md or fresh fetch)
    7. Inst ownership < 70% (room for marginal buyer)
    8. Stock reaction +1–3 days post

    Status: ✅ confirmed, ⚠ warning, ❌ fail, ❓ TBD pending print.

  5. Max-pain interplay note — pull weekly + monthly max pain (chartexchange.com/symbol/<EX>-$ARGUMENTS/optionchain/summary/). State whether the magnetic level pulls into or away from the print, and the post-print magnet for the following month.

  6. Pre-print read — synthesize: Constructive / Neutral / Bearish into the print. Cite which checklist items drive the read.

  7. Edit only the Earnings setup section of scanned/stocks/$ARGUMENTS/current.md. Leave 6-Pillar / Technical Read / Trade plan untouched.

  8. If a horizon-specific trigger fires post-print (e.g., a Swing-tier "watch close above $X on green vector" that the print delivered or failed to), log to scanned/INDEX.md § Performance / audit log. The earnings outcome may also force a tier transition — apply per tiers.md § Tier-change protocol.

  9. No archive rotation, no rescan rotation — in-place update. Full audit trail comes from /rescan only.

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. 10d ago First seen · 44 lines · 16 tokens per session scan A 49845f95ca26

Subscribe to this mod's changes

scan-earnings is a command published in the GitHub repository l3lackcurtains/trading-ops (56 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 650 once invoked, about $0.0001 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.