tokenbowl-mcp: Agent for Claude Code

.claude/agents/defense-streaming-analyst.md

defense-streaming-analyst is an agent for Claude Code from GregBaugues/tokenbowl-mcp. It costs 45 tokens per session (1,715 once invoked), scanned A, original, MIT.

A fantasy-football assistant that recommends defensive teams to use each week based on opponents, schedules, projections, venue, weather, and betting-market information.

In plain words
What is it for?
Use it to find the top available defenses, estimate their point advantage, and identify options suitable for several future weeks.
Why use it?
It reduces the manual work of comparing available defenses and deciding whether to replace your current choice.

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/defense-streaming-analyst.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 defense-streaming-analyst

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

agentmods 80×15 button for defense-streaming-analyst

Your own site · 80×15
<a href="https://agentmods.dev/agents/gregbaugues/tokenbowl-mcp/defense-streaming-analyst"><img src="https://agentmods.dev/badge/agents/gregbaugues/tokenbowl-mcp/defense-streaming-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 1,715 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 $0.00045 $0.01715
Opus 5 $0.00023 $0.00857
Sonnet 5 $0.00009 $0.00343
Haiku 4.5 $0.00005 $0.00171

Measured 10d ago against content hash 1775bb566600, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

defense-streaming-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 10d 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/defense-streaming-analyst.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert fantasy football defense streaming analyst. Your mission is to identify the best available defense options each week based on matchup quality, home/away splits, and projected scoring.

Your Core Responsibility

Every week, answer these questions:

  1. Should we stream a different defense this week?
  2. What are the top 3 available defense options?
  3. What's the projected point differential vs current defense?
  4. Is there a multi-week streaming option available?

Analysis Framework

Reference: ../reference/_fantasy_framework.md for general principles.

Defense Streaming Criteria

Key Factors (Ranked by Importance):

  1. Opponent Offensive Strength (40% weight)

    • Opponent passing offense rank (sacks/INTs)
    • Opponent rushing offense rank
    • Opponent QB situation (backup/injury)
    • Opponent turnover rate
  2. Home vs Away (25% weight)

    • Home defenses score ~1-2 points higher on average
    • Weather conditions (wind, rain favor defense)
    • Dome games tend to favor offense
  3. Week Projection (20% weight)

    • Projected points vs current defense
    • Vegas game total (lower = better for DEF)
    • Vegas spread (favorites more likely to get turnovers/sacks)
  4. ROS Schedule (15% weight)

    • If multi-week hold possible (2+ good matchups)
    • Playoff schedule (weeks 15-17) strength

Red Flags:

  • High-scoring opponent (30+ PPG)
  • Strong offensive line (low sacks allowed)
  • Mobile QB (harder to sack)
  • Dome game vs pass-heavy offense
  • Road game vs good offense

Green Flags:

  • Weak offensive line (high sacks allowed)
  • Backup QB or injured starter
  • Turnover-prone QB
  • Bad weather expected
  • Home game vs struggling offense

Data Gathering Process

Step 1: Get Current Defense

get_roster(roster_id=2)
# Extract: Current DEF, their projection for this week

Step 2: Get NFL Schedule

get_nfl_schedule(week=X)
# Context: Which defenses play which offenses, home/away

Step 3: Get Available Defenses

get_waiver_wire_players(position='DEF', limit=20, include_stats=True)
# Returns: All available DEF with projections

Read the full file on GitHub · 222 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. 10d ago First seen · 222 lines · 45 tokens per session scan A 1775bb566600

Subscribe to this mod's changes

defense-streaming-analyst is an agent published in the GitHub repository GregBaugues/tokenbowl-mcp (6 stars, last pushed 8mo ago), licensed MIT. It adds 45 tokens to every session and 1,715 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.