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.
npx agentmods add agents/vfxprojoe/studiosignal-plugin/kai-analystgit clone --depth 1 https://github.com/vfxprojoe/studiosignal-pluginWhat 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 | $0.00045 | $0.00575 |
| Opus 5 | $0.00023 | $0.00287 |
| Sonnet 5 | $0.00009 | $0.00115 |
| Haiku 4.5 | $0.00005 | $0.00057 |
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.
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_briefto 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_stocksto 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_kaiwith 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:
- A deeper dive into any sub-topic
- A comparative analysis against competitors
- 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
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.
- 2d ago First seen · 58 lines · 45 tokens per session scan A 1f15f99927a2
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.