agentleFS
SKE-LabsSKE-Labs/agent-trading-skills/skills/fundamental-analysis/insider-activity-trading/SKILL.md

insider-activity-trading

Skill17 starsChanged 4 months agoApache-2.0View on GitHub

Parse and evaluate SEC insider filings as delayed contextual evidence. Use when analyzing Form 4 codes, holdings changes, footnotes, amendments, purchase/sale clusters, and 10b5-1 disclosures.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use insider filings as delayed, contextual evidence.

    line 12
  2. Distinctive:

    Look for: recent Form 4 filings, transaction size, buyer/seller role, and whether purchases are scheduled (10b5-1) or discretionary.

    line 59
  3. Distinctive:

    Treat the setup as a testable hypothesis, not a prediction.

    line 74
  4. Distinctive:

    Never trade on a headline.

    line 82
  5. Distinctive:

    Do not equate a 10b5-1 label with neutrality or a transaction with a disclosed motive.

    line 83
  6. Distinctive:

    Use filing availability time—not transaction time—to prevent look-ahead bias.

    line 85

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Insider Activity Trading

Use insider filings as delayed, contextual evidence. A transaction may reflect valuation views, compensation, taxes, liquidity needs, ownership policy, or a trading plan; it does not reveal motive by itself.

Filing Fields

Record issuer, insider role, filing and transaction timestamps, direct/indirect ownership, transaction code, price, shares, post-transaction holdings, footnotes, derivative status, and 10b5-1 disclosure. Confirm amendments and avoid double counting the same beneficial owner.

Signal Interpretation

Open-Market Purchases

FactorStronger Signal
Multiple independent insiders buyingCandidate cluster; define window before testing
Large purchasesMeaningful % of holdings
After price dropBuying the dip
C-suite buyingCEO/CFO conviction

Sales and Other Codes

Separate open-market purchases/sales (P/S) from grants, option exercises, tax withholding, gifts, and other codes. Read footnotes and plan disclosures; even an open-market purchase or sale has an unobserved motive.

Selling ReasonSignal Strength
Planned (10b5-1)Contextual; inspect adoption date, terms, and amendments
DiversificationWeak negative
After big run-upModerate negative
Unusual amountStronger negative
Multiple C-suite sellingCandidate cluster requiring plan/code/holdings context

Bullish vs Bearish Patterns

BullishBearish
CEO buying the dipMultiple C-suite selling
Independently defined purchase clusterSelling right after guidance
Large $ purchases on weaknessUnusual volume of sales
Buying after bad newsSelling before scheduled news

Workflow

1. Research Insider Activity

get_financial_news(topic="AAPL insider buying selling SEC Form 4 filing", max_results=15)
get_fundamentals(ticker="AAPL")

Look for: recent Form 4 filings, transaction size, buyer/seller role, and whether purchases are scheduled (10b5-1) or discretionary.

2. Assess Pattern

  • Single insider selling = low signal, check if 10b5-1 planned
  • Single insider buying = moderate signal, check size relative to holdings
  • Purchase cluster = count independent insiders within a predeclared window and compare with issuer history
  • C-suite selling unusual amounts = red flag, investigate further

3. Combine with Fundamentals

Insider activity is a confirming signal, not standalone. Cross-reference with company fundamentals, recent earnings, and technical setup before acting.

Evidence and Validation

  • Treat the setup as a testable hypothesis, not a prediction. Define thresholds, entry, invalidation, and exit before evaluating outcomes.
  • Calibrate on the same instrument, venue, session, and timeframe. Use closed candles and a held-out or walk-forward sample; record every variant tried.
  • Include spread, fees, slippage, borrow or funding, partial fills, and latency. Reject the setup when net expectancy is not positive or depends on one narrow parameter.
  • Return observed inputs, missing data, cost assumptions, entry, invalidation, exit, and a valid, watch, or no-trade status.
  • Research basis: The SEC Form 3/4/5 bulletin explains codes and two-business-day reporting, while the 10b5-1 rule requires plan-related disclosures.

Key Rules

  • Never trade on a headline; parse the filed form, codes, footnotes, ownership, and amendments.
  • Do not equate a 10b5-1 label with neutrality or a transaction with a disclosed motive.
  • Normalize transaction value by prior holdings, compensation, market capitalization, and insider history.
  • Use filing availability time—not transaction time—to prevent look-ahead bias; Form 4 is generally due within two business days, subject to form rules.
  • Define cluster windows and event exclusions before testing; report no trade when context is missing.

Related Skills

  • earnings-trading -- Insider activity around earnings signals management confidence
  • sentiment-analysis -- Insider buying is a high-credibility input to sentiment scoring

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.