public-equity-research: Skill for Claude Code

.claude/skills/market-router/SKILL.md

market-router is a skill for Claude Code from lowtidebuild/public-equity-research. It costs 0 tokens per session (3,492 once invoked), scanned A, original, Apache-2.0.

A market-research routing tool that checks available data sources, identifies the type of company and its peers, and prepares a research plan for a stock ticker.

In plain words
What is it for?
It is for setting up stock research, selecting data sources, classifying companies, finding comparable businesses, and writing the searches and analysis plan for a research run.
Why use it?
It chooses between enhanced and standard research based on which data connections work, while accounting for markets that need a different approach. It also creates a local place to store the research outputs.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is lowtidebuild/public-equity-research's own configuration. It tells Claude Code how to work on public-equity-research 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 public-equity-research configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python .claude/skills/data-manager/scripts/artifact-manager.py init --tickers {ticker}.

Reuse

Borrowing it

Nothing to install: this file belongs to lowtidebuild/public-equity-research. 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/lowtidebuild/public-equity-research/main/.claude/skills/market-router/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lowtidebuild/public-equity-research

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 market-router

README.md
[![agentmods](https://agentmods.dev/badge/skills/lowtidebuild/public-equity-research/market-router/github.svg)](https://agentmods.dev/skills/lowtidebuild/public-equity-research/market-router)
Your own site
<a href="https://agentmods.dev/skills/lowtidebuild/public-equity-research/market-router"><img src="https://agentmods.dev/badge/skills/lowtidebuild/public-equity-research/market-router/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 market-router

Your own site · 80×15
<a href="https://agentmods.dev/skills/lowtidebuild/public-equity-research/market-router"><img src="https://agentmods.dev/badge/skills/lowtidebuild/public-equity-research/market-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,492 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00000 $0.03492
Opus 5 $0.00000 $0.01746
Sonnet 5 $0.00000 $0.00698
Haiku 4.5 $0.00000 $0.00349

Measured 12d ago against content hash 9b39e96a1778, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

market-router 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 12d 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/skills/market-router/SKILL.md · 295 lines

How it starts

The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Market Router — SKILL.md

Role: Step 2 — Detect MCP availability, determine data mode (Enhanced/Standard), classify company type, identify peers, initialize a run-local artifact root, and write the research plan. Triggered by: CLAUDE.md after Step 1 (query interpretation) Reads: Session state from Step 1, references/company-type-classification.md Writes: output/runs/{run_id}/{ticker}/research-plan.json References: company-type-classification.md


Instructions

Step 2.1 — MCP Availability Detection

Always perform this check at session start (cached for the session — do not repeat per ticker).

Test call:

get_current_stock_price("<TICKER>")
Result Decision
Valid price returned Enhanced Mode available
Error / timeout Retry once after 2 seconds
Second failure Standard Mode (yfinance + targeted web)
Korean stock (any market) Always Standard Mode regardless of MCP

Korean stocks are ALWAYS Standard Mode — Financial Datasets MCP does not support KRX.

Cache the result as session variable: DATA_MODE = "enhanced" | "standard"

Log:

MCP check: get_current_stock_price("<TICKER>") -> {result}
DATA_MODE: {enhanced/standard}

Step 2.2 — Company Type Classification

Read company-type-classification.md. Classify based on:

  1. Ticker/company name lookup (known companies)
  2. Sector from API (get_financial_metrics sector field, Enhanced Mode only)
  3. Web search: "{ticker}" sector industry classification site:finance.yahoo.com
  4. Keyword matching in company name

Multi-segment rule: if company has 2+ segments with different economics (e.g., cloud + hardware, banking + insurance), classify as the primary revenue segment type, then note the secondary type.

Output classification with confidence:

  • HIGH: ticker found in known list or API sector confirmed
  • MEDIUM: inferred from keywords or partial data
  • LOW: unknown, using "Other" as fallback

Step 2.3 — Peer Identification

Read the full file on GitHub · 295 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 295 lines · 0 tokens per session scan A 9b39e96a1778

Subscribe to this mod's changes

market-router is a skill published in the GitHub repository lowtidebuild/public-equity-research (46 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,492 tokens. 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.