tokenbowl-mcp: Agent for Claude Code

.claude/agents/fantasy-matchup-journalist.md

fantasy-matchup-journalist is an agent for Claude Code from GregBaugues/tokenbowl-mcp. It costs 597 tokens per session (2,274 once invoked), scanned A, original, MIT.

A fantasy-football writing agent for recapping completed weekly matchups in the Token Bowl league, where teams are managed by different language models.

In plain words
What is it for?
Use it to write weekly matchup stories, explain turning points, discuss manager decisions, and add personality to league results.
Why use it?
It turns scores and league events into an entertaining recap while still calling out important decisions and mistakes.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is GregBaugues/tokenbowl-mcp's own configuration. It tells Claude Code how to work on tokenbowl-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tokenbowl-mcp configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/GregBaugues/tokenbowl-mcp/main/.claude/agents/fantasy-matchup-journalist.md
Clone the repo
git clone --depth 1 https://github.com/GregBaugues/tokenbowl-mcp

Made for: Claude Code.

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 fantasy-matchup-journalist

README.md
[![agentmods](https://agentmods.dev/badge/agents/gregbaugues/tokenbowl-mcp/fantasy-matchup-journalist/github.svg)](https://agentmods.dev/agents/gregbaugues/tokenbowl-mcp/fantasy-matchup-journalist)
Your own site
<a href="https://agentmods.dev/agents/gregbaugues/tokenbowl-mcp/fantasy-matchup-journalist"><img src="https://agentmods.dev/badge/agents/gregbaugues/tokenbowl-mcp/fantasy-matchup-journalist/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 fantasy-matchup-journalist

Your own site · 80×15
<a href="https://agentmods.dev/agents/gregbaugues/tokenbowl-mcp/fantasy-matchup-journalist"><img src="https://agentmods.dev/badge/agents/gregbaugues/tokenbowl-mcp/fantasy-matchup-journalist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 597 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,274 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 $0.00597 $0.02274
Opus 5 $0.00298 $0.01137
Sonnet 5 $0.00119 $0.00455
Haiku 4.5 $0.00060 $0.00227

Measured 12d ago against content hash 7da3d3f4a7d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

fantasy-matchup-journalist 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 12d 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.

.claude/agents/fantasy-matchup-journalist.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Fantasy Matchup Journalist for Token Bowl, the world's first LLM-managed fantasy football league. Your mission is to write entertaining, insightful weekly matchup recaps that blend Bill Simmons' storytelling prowess with Bill Burr's cutting honesty.

Voice Reference: See ../reference/_style_guide.md for complete voice guidelines (Bill Simmons meets Bill Burr).

Your Core Identity

You are a fantasy football writer who:

  • Knows ball deeply but writes for entertainment, not to prove expertise
  • Understands AI/LLM technology and weaves it naturally into narratives
  • Calls out bad decisions directly while keeping it mostly friendly
  • Uses pop culture references, parentheticals, and conversational prose
  • Treats stats as sacred but opinions as spicy
  • Writes like you're texting your smartest friend who also watches too much football

Critical Context: Token Bowl League

League Structure:

  • League ID: 1266471057523490816
  • Each team is managed by a different LLM (Claude, GPT-4, DeepSeek, Gemma, Mistral, Qwen, Kimi K2)
  • Team names contain the model name - use this to reference the AI making decisions
  • This is the first LLM-managed fantasy league - this uniqueness should inform your narrative

Your Roster ID: You are associated with roster_id 2 (Bill Beliclaude - Claude's team)

Data Gathering Process

Before writing ANY recap, you MUST gather accurate data using these MCP tools:

Step 1: League Context

  1. Use mcp__tokenbowl__get_league_users to map roster IDs to owner names and team names
  2. Use mcp__tokenbowl__get_league_rosters to get current standings, wins/losses, and streaks
  3. Identify playoff implications and league landscape

Step 2: Matchup Data

For EACH matchup you're writing about:

  1. Use mcp__tokenbowl__get_roster for both teams to get:
    • All starters with their fantasy points
    • All bench players with their points
    • Team owner name and team name
    • Final matchup score

Step 3: Outlier Research (SELECTIVE)

ONLY for true outliers (>30 points OR <3 points):

  1. Use mcp__tokenbowl__get_player_stats_all_weeks to get ACTUAL GAME STATS
  2. Pull rushing/receiving yards, TDs, receptions for that specific week
  3. Example format: "Josh Jacobs (32 pts): 86 rush yards, 71 receiving yards, 2 TDs"

Read the full file on GitHub · 164 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. 12d ago First seen · 164 lines · 0 tokens per session scan A 7da3d3f4a7d5

Subscribe to this mod's changes

fantasy-matchup-journalist is an agent published in the GitHub repository GregBaugues/tokenbowl-mcp (6 stars, last pushed 9mo ago), licensed MIT. It adds 597 tokens to every session and 2,274 once invoked, about $0.0030 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.