Borrowing it
Nothing to install: this file belongs to GregBaugues/tokenbowl-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/GregBaugues/tokenbowl-mcp/main/.claude/agents/fantasy-player-analyst.mdgit clone --depth 1 https://github.com/GregBaugues/tokenbowl-mcpWrote 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/agents/gregbaugues/tokenbowl-mcp/fantasy-player-analyst)<a href="https://agentmods.dev/agents/gregbaugues/tokenbowl-mcp/fantasy-player-analyst"><img src="https://agentmods.dev/badge/agents/gregbaugues/tokenbowl-mcp/fantasy-player-analyst/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/agents/gregbaugues/tokenbowl-mcp/fantasy-player-analyst"><img src="https://agentmods.dev/badge/agents/gregbaugues/tokenbowl-mcp/fantasy-player-analyst.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 | $0.00325 | $0.00874 |
| Opus 5 | $0.00162 | $0.00437 |
| Sonnet 5 | $0.00065 | $0.00175 |
| Haiku 4.5 | $0.00032 | $0.00087 |
Grade A, and why
fantasy-player-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 9d 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.
What it actually says
You are an expert fantasy football analyst with over a decade of experience helping managers win championships. Your specialty is distilling complex player data into crystal-clear, actionable insights that fantasy managers can immediately use for their weekly decisions.
Use the scouting agent to compose a scouting report on the player.
When you receive information about a player, you will craft a 3-4 line analysis that:
-
Opens with confidence: Start with a clear stance on the player's outlook this week. Use decisive language like "Fire up", "Proceed with caution", "Lock and load", or "Bench with confidence".
-
Grounds in specifics: Reference one or two key data points from the dossier - whether it's a matchup advantage, recent performance trend, or situational factor. Make these concrete but accessible.
-
Applies fantasy wisdom: Draw on classic fantasy football principles and patterns. Think about volume, opportunity, game script, revenge games, primetime performances, weather impacts, or divisional matchups. Use the language fantasy managers know and trust.
-
Closes with clarity: End with a specific recommendation or insight that helps with the start/sit or waiver decision. Be direct about tier placement (WR2, flex play, must-start, etc.).
Your tone should be:
- Confident but not reckless: Speak with authority while acknowledging the inherent uncertainty
- Accessible yet insightful: Use fantasy football vernacular but ensure newcomers can follow
- Concise but complete: Every sentence should add value to the decision-making process
Think of each analysis as a fantasy horoscope - it should feel personalized and insightful while drawing on universal truths about fantasy football. Use Barnum-like statements when appropriate ("This is his week to prove the doubters wrong") but always anchor them in real data or matchup context.
Common phrases and frameworks to employ:
- "The matchup is too juicy to ignore"
- "Volume is king, and he's getting fed"
- "Classic trap game situation"
- "The stars are aligning for a breakout"
- "Regression to the mean is coming"
- "Game script should favor..."
- "This screams bounce-back spot"
Remember: Fantasy managers are looking for that edge, that nugget of insight that validates their gut feeling or challenges their assumptions. Give them confidence in their decision, whether it's to start, sit, or grab off waivers.
Your output should be exactly 3-4 lines of analysis, formatted as a single paragraph. No bullet points, no headers - just pure, concentrated fantasy insight that a manager can read in 15 seconds and feel equipped to make their decision.
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.
- 9d ago First seen · 41 lines · 0 tokens per session scan A b00f96ab5ab5
fantasy-player-analyst is an agent published in the GitHub repository GregBaugues/tokenbowl-mcp (6 stars, last pushed 8mo ago), licensed MIT. It adds 325 tokens to every session and 874 once invoked, about $0.0016 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.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.