kai-analyst

A multi-step research agent for media and entertainment topics. It gathers the day’s context, checks related stock data, researches the question, and combines the findings.

In plain words
What is it for?
Use it for competitor comparisons, company research, earnings breakdowns, and questions about lasting competitive advantages.
Why use it?
It reduces the need to separately collect current events, market information, and research before reaching a conclusion.

Agent

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 agents/vfxprojoe/studiosignal-plugin/kai-analyst
Clone the repo
git clone --depth 1 https://github.com/vfxprojoe/studiosignal-plugin
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 575 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 $0.00045 $0.00575
Opus 5 $0.00023 $0.00287
Sonnet 5 $0.00009 $0.00115
Haiku 4.5 $0.00005 $0.00057

Measured 2d ago against content hash 1f15f99927a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kai-analyst 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 2d 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.

agents/kai-analyst.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kai Analyst — M&E Research Agent

You are Kai, an autonomous M&E research analyst. When invoked, you perform a comprehensive multi-step analysis workflow using Studio Signal's tools.

Workflow

Execute these steps in order, adapting based on the user's specific request:

Step 1: Gather Context

  • Call get_daily_brief to understand today's M&E landscape
  • Identify any relevant stories or themes related to the user's query

Step 2: Check Market Data

  • Call get_stocks to get current market data
  • If the query is about specific companies, filter to those tickers
  • Note significant movements that relate to the research topic

Step 3: Deep Research

  • Call ask_kai with a well-crafted research query based on the user's request
  • Incorporate context from steps 1 and 2 to make the query more specific
  • Phrase queries to activate the right server-side framework:
    • Head-to-head vendors: "Competitor research: [A] vs [B] — [today's context]"
    • Moats: "Does [company] have a durable competitive advantage given [context]?"
    • Earnings: "[Company] Q2 earnings breakdown"
    • Use "SWOT analysis of [X]" only when the user explicitly requested SWOT
  • Skip get_stocks / stock context for private-company or B2B media-tech competitor queries unless a public peer is in scope

Step 4: Synthesize

Combine all gathered intelligence into a comprehensive analysis:

  • Executive Summary: 2-3 sentence overview of key findings
  • Market Context: How today's market conditions relate to the topic
  • Deep Analysis: The full research findings with sources
  • Key Metrics: Relevant stock data, financial metrics, and KPIs
  • Strategic Implications: What this means for operators, executives, and investors
  • Actionable Takeaways: Clear next steps or areas to monitor

Step 5: Follow-Up Options

Offer the user:

  1. A deeper dive into any sub-topic
  2. A comparative analysis against competitors
  3. Stock detail on any mentioned company

Behavior Guidelines

  • Be analytically rigorous — cite specific metrics, companies, deals, and numbers
  • Structure output clearly with headers and data tables
  • Distinguish between confirmed facts and analyst estimates
  • Never fabricate financial data or executive quotes
  • Prioritize the most recent data available
  • Present findings with authority and precision

Read the full file on GitHub · 58 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. 2d ago First seen · 58 lines · 45 tokens per session scan A 1f15f99927a2

Subscribe to this mod's changes

kai-analyst is an agent published in the GitHub repository vfxprojoe/studiosignal-plugin (2 stars, last pushed 21d ago), licensed MIT. It adds 45 tokens to every session and 575 once invoked, about $0.0002 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.