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.
curl -O https://raw.githubusercontent.com/l3lackcurtains/trading-ops/main/.claude/commands/scan-earnings.mdgit clone --depth 1 https://github.com/l3lackcurtains/trading-opsWrote 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/commands/l3lackcurtains/trading-ops/scan-earnings)<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.
<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>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 | $0.00016 | $0.00650 |
| Opus 5.5 | $0.00006 | $0.00260 |
| Sonnet 5.5 | $0.00003 | $0.00130 |
| Haiku 4.5 | $0.00002 | $0.00065 |
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 1mo 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.
What it actually says
Run an earnings-only scan for: $ARGUMENTS
Partial scan — updates only the Earnings setup section. Use during the 7–14 days before a print, or immediately post-print to record the reaction.
Protocol in guide/scan/ — see structure.md for the section format and data.md for sourcing.
Steps
-
Verify
scanned/stocks/$ARGUMENTS/current.mdexists. If not, tell the user to run/scan $ARGUMENTSfirst. -
Read-before-scan per
protocol.md— capture prior earnings setup notes if any (especially the 8-point checklist if it was already partly filled). -
Pull earnings data per
data.md:- Finviz quote page (next earnings date, EPS estimate)
- Seeking Alpha for transcripts, guidance, capital allocation tone (
seekingalpha.com/symbol/$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
-
Run 8-point pre-print checklist:
- EPS ≥ 25% YoY accelerating
- Revenue ≥ 25% YoY 3rd consecutive quarter
- FCF up alongside net income
- Margins expanding or holding
- Mgmt raised guidance
- Inst holders increased (per Pillar 6 from prior
current.mdor fresh fetch) - Inst ownership < 70% (room for marginal buyer)
- Stock reaction +1–3 days post
Status: ✅ confirmed, ⚠ warning, ❌ fail, ❓ TBD pending print.
-
Max-pain interplay note — pull weekly + monthly max pain (
chartexchange.com/symbol/<EX>-$ARGUMENTS/optionchain/summary/). State whether the magnetic level pulls into or away from the print, and the post-print magnet for the following month. -
Pre-print read — synthesize: Constructive / Neutral / Bearish into the print. Cite which checklist items drive the read.
-
Edit only the Earnings setup section of
scanned/stocks/$ARGUMENTS/current.md. Leave 6-Pillar / Technical Read / Trade plan untouched. -
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 pertiers.md§ Tier-change protocol. -
No archive rotation, no rescan rotation — in-place update. Full audit trail comes from
/rescanonly.
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.
- 1mo ago First seen · 44 lines · 16 tokens per session scan A 49845f95ca26
scan-earnings is a command published in the GitHub repository l3lackcurtains/trading-ops (57 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 650 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
performance
Generate a strategy performance report with key metrics.
execute-entry
Execute a new MEICAgent iron condor entry. Only invoke when the entry decision (Step 6) is yes.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.