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.
/plugin marketplace add cimomo/intrinsic/plugin install intrinsicWrote 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/skills/cimomo/intrinsic/research)<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.
<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>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 | $0.00010 | $0.01840 |
| Opus 5 | $0.00005 | $0.00920 |
| Sonnet 5 | $0.00002 | $0.00368 |
| Haiku 4.5 | $0.00001 | $0.00184 |
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.
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
StockManagerfromstock_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 $ARGUMENTSfirst, 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
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.
- 8d ago First seen · 177 lines · 10 tokens per session scan A 42df503ba9c2
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.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.