thesis-tracker

thesis-tracker is a skill for Claude Code, Codex from ginlix-ai/LangAlpha. It costs 21 tokens per session (580 once invoked), scanned A, original, Apache-2.0.

A scorecard for tracking an investment idea over time. It records the reasons for buying or selling a company, the risks that could disprove the idea, upcoming events, valuation, and changes in confidence.

In plain words
What is it for?
Use it to create or update a company investment thesis, assess supporting arguments and risks, track catalysts such as earnings or launches, and record decisions like holding, buying more, trimming, or exiting.
Why use it?
It keeps new facts connected to the original investment reasoning instead of treating each news event in isolation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

About the project

LangAlpha is an agent workspace for researching financial markets and supporting investment decisions through persistent research, news analysis, and parallel subagents. It is for investors who want to develop and update trading theses over time, including generating long-short pair-trade ideas. The catalogue entries provide the skills, instructions, MCP servers, and plugin that make up its agent workflow.

ginlix-ai/LangAlpha · 1,722 stars · on GitHub · langalpha.ai

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/ginlix-ai/langalpha/thesis-tracker
Any agent
npx skills add ginlix-ai/LangAlpha --skill thesis-tracker
Clone the repo
git clone --depth 1 https://github.com/ginlix-ai/LangAlpha

Made for: Claude Code, Codex.

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 thesis-tracker

README.md
[![agentmods](https://agentmods.dev/badge/skills/ginlix-ai/langalpha/thesis-tracker.svg)](https://agentmods.dev/skills/ginlix-ai/langalpha/thesis-tracker)
Your own site
<a href="https://agentmods.dev/skills/ginlix-ai/langalpha/thesis-tracker"><img src="https://agentmods.dev/badge/skills/ginlix-ai/langalpha/thesis-tracker.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 580 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00021 $0.00580
Opus 5 $0.00010 $0.00290
Sonnet 5 $0.00004 $0.00116
Haiku 4.5 $0.00002 $0.00058

Measured 6d ago against content hash d6c987d18d50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

thesis-tracker 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 6d 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.

plugins/langalpha_research/skills/thesis-tracker/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Thesis Tracker

Workflow

Step 1: Define or Load Thesis

If creating a new thesis:

  • Company: Name and ticker
  • Position: Long or Short
  • Thesis statement: 1-2 sentence core thesis (e.g., "Long ACME — margin expansion from pricing power + operating leverage as mix shifts to software")
  • Key pillars: 3-5 supporting arguments
  • Key risks: 3-5 risks that would invalidate the thesis
  • Catalysts: Upcoming events that could prove/disprove the thesis (earnings, product launches, regulatory decisions)
  • Target price / valuation: What's it worth if the thesis plays out
  • Stop-loss trigger: What would make you exit

If updating an existing thesis, ask the user for the new data point or development.

Step 2: Update Log

For each new data point or development:

  • Date: When this happened
  • Data point: What changed (earnings beat, management departure, competitor move, etc.)
  • Thesis impact: Does this strengthen, weaken, or neutralize a specific pillar?
  • Action: No change / Increase position / Trim / Exit
  • Updated conviction: High / Medium / Low

Step 3: Thesis Scorecard

Maintain a running scorecard:

Pillar Original Expectation Current Status Trend
Revenue growth >20% On track Q3 was 22% Stable
Margin expansion Behind Margins flat YoY Concerning
New product launch Pending Delayed to Q2 Watch

Step 4: Catalyst Calendar

Track upcoming catalysts:

Date Event Expected Impact Notes

Step 5: Output

Thesis summary suitable for:

  • Morning meeting discussion
  • Portfolio review
  • Risk committee presentation

Format: Concise markdown or Word doc with the scorecard, recent updates, and current conviction level.

Important Notes

  • A thesis should be falsifiable — if nothing could disprove it, it's not a thesis
  • Track disconfirming evidence as rigorously as confirming evidence
  • Review theses at least quarterly, even when nothing dramatic has happened
  • If the user manages multiple positions, offer to do a full portfolio thesis review
  • Store thesis data in a structured format so it can be referenced across sessions

Read the full file on GitHub · 69 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.

  1. 6d ago First seen · 69 lines · 21 tokens per session scan A d6c987d18d50

Subscribe to this mod's changes

thesis-tracker is a skill published in the GitHub repository ginlix-ai/LangAlpha (1,722 stars, last pushed today), licensed Apache-2.0. It adds 21 tokens to every session and 580 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.