research

research is a skill for Claude Code from cimomo/intrinsic. It costs 10 tokens per session (1,840 once invoked), scanned A, original, MIT.

A qualitative stock-research workflow that examines a company's business, growth outlook, competitive position, profits, use of capital, risks, and key debate. Its output is a structured research document for later valuation and reporting.

In plain words
What is it for?
Use it to research how a company makes money, assess its competitive position and growth, identify risks, and prepare inputs for valuation assumptions.
Why use it?
It records the business context and non-numerical factors that financial figures alone may miss.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the intrinsic plugin — 6 skills shipped together

Good fit Use it to research how a company makes money, assess its competitive position and growth, identify risks, and prepare inputs for valuation assumptions.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add cimomo/intrinsic
Claude Code
/plugin install intrinsic

Made for: Claude Code.

Or install intrinsic, the plugin that ships this one along with the rest of its 6 skills.

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 research

README.md
[![agentmods](https://agentmods.dev/badge/skills/cimomo/intrinsic/research/github.svg)](https://agentmods.dev/skills/cimomo/intrinsic/research)
Your own site
<a href="https://agentmods.dev/skills/cimomo/intrinsic/research"><img src="https://agentmods.dev/badge/skills/cimomo/intrinsic/research/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 research

Your own site · 80×15
<a href="https://agentmods.dev/skills/cimomo/intrinsic/research"><img src="https://agentmods.dev/badge/skills/cimomo/intrinsic/research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,840 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 $0.00010 $0.01840
Opus 5 $0.00005 $0.00920
Sonnet 5 $0.00002 $0.00368
Haiku 4.5 $0.00001 $0.00184

Measured 8d ago against content hash 42df503ba9c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

research 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 8d 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.

skills/research/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Perform qualitative research and analysis for ticker symbol $ARGUMENTS.

The research output serves two purposes: (1) provide structured qualitative intelligence that feeds into /calibrate (calibrate) and /report, and (2) be a useful standalone document for the user.

Python Environment

When running Python code, set PYTHONPATH so stock_analyzer is importable:

PYTHONPATH="${CLAUDE_PLUGIN_ROOT:-.}" python3 -c "from stock_analyzer import ..."

Output Template

The research document MUST follow this structure exactly. Every signal field MUST have a value.

# {Company} ({TICKER}) — Research
**Date:** YYYY-MM-DD

## Business Context
[2-3 sentences: what the company does, how it makes money, scale]

## Growth Outlook
**Growth signal:** Accelerating / Stable / Decelerating
**Confidence:** High / Medium / Low
[prose]

## Competitive Position & Moat
**Moat:** Wide / Narrow / None
**Direction:** Widening / Stable / Narrowing
[prose]

## Margin & Profitability
**Margin signal:** Expanding / Stable / Compressing
[prose]

## Capital Efficiency
**Capital intensity:** Light / Moderate / Heavy
[prose]

## Key Risks
[2-3 material risks only]

## Key Debate
[prose]

Steps:

1. Load Financial Data for Context

  • Initialize StockManager from stock_analyzer.stock_manager
  • Try StockManager.load_financial_data("$ARGUMENTS") to check for cached data
  • If cached data exists: Use it (display "Using cached data from {fetched_at}")
  • If no cached data: Invoke /fetch $ARGUMENTS first, then load the cached data
  • If no data available at all (fetch failed, no API key): Proceed with web-only research. Note in the output: "Research based on public sources only — no financial data context available."

2. Identify Questions from the Data

Before searching, review the financial data for anything surprising or unclear. Examples:

  • Revenue growth changing direction (accelerating/decelerating)
  • Margin anomalies (sudden expansion or compression)
  • CapEx spikes or drops
  • Unusual debt changes or large acquisitions on the balance sheet
  • Cash flow diverging from net income
  • Quarterly volatility vs smooth annual trends

Read the full file on GitHub · 177 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. 8d ago First seen · 177 lines · 10 tokens per session scan A 42df503ba9c2

Subscribe to this mod's changes

research is a skill published in the GitHub repository cimomo/intrinsic (4 stars, last pushed 4mo ago), licensed MIT. It adds 10 tokens to every session and 1,840 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 2026-08-31.

Related

Other skills, from other repositories