tokenbowl-mcp: Command for Claude Code

.claude/commands/startsit.md

startsit is a command for Claude Code from GregBaugues/tokenbowl-mcp. It costs 0 tokens per session (913 once invoked), scanned A, original, MIT.

A fantasy-football lineup command that reviews one roster and recommends which players to start, bench, or use in the flex position for the current week.

In plain words
What is it for?
Use it to build a weekly starting lineup from starters and bench players, flag players who cannot play because of a bye week, and compare flex or defense options.
Why use it?
It reduces the manual work of checking bye weeks, matchups, recent form, projections, and defense choices before setting a lineup.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

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/commands/startsit.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 startsit

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/gregbaugues/tokenbowl-mcp/startsit"><img src="https://agentmods.dev/badge/commands/gregbaugues/tokenbowl-mcp/startsit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 913 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 $0.00000 $0.00913
Opus 5 $0.00000 $0.00456
Sonnet 5 $0.00000 $0.00183
Haiku 4.5 $0.00000 $0.00091

Measured 9d ago against content hash 62296602ae12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

startsit 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.

.claude/commands/startsit.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Start/Sit Analysis

Analyze the Bill Beliclaude roster (Roster ID 2) and provide detailed start/sit recommendations for the current week.

Goal

Construct optimal weekly lineup by:

  1. Analyzing all roster players (starters + bench)
  2. Identifying bye week players (cannot start)
  3. Evaluating matchups and recent form
  4. Making flex decisions based on upside
  5. Assessing defense streaming options

Reference: See .claude/reference/_fantasy_framework.md for evaluation criteria.

Execution Phases

Phase 1: Gather Roster Data

get_roster(roster_id=2)

Extract:

  • Current week number (use this for ALL subsequent operations)
  • All starters and bench players with projections
  • Each player's bye_week field
get_nfl_schedule(week=<week_from_roster_data>)

Shows game times and matchups for context.

CRITICAL: Identify bye week players by comparing player.bye_week == current_week. These players have 0.0 projected points and cannot be started.

Phase 2: Player Analysis

Use the fantasy-player-analyst subagent to analyze ALL roster players (starters + bench).

Week outlooks: MUST START / START / FLEX / SIT / ON BYE

Critical: Flag bye week players (bye_week == current_week) as "ON BYE THIS WEEK - Cannot start"

Phase 3: Lineup Construction

Step 1: Lock in MUST START Players
  • QB, RB1, RB2, WR1, WR2, TE if no better option
  • Exclude any player where bye_week == current_week
Step 2: Identify Flex Competition
  • List all viable flex candidates (WR3+, RB3+, TE2 if applicable)
  • EXCLUDE any player on bye this week
  • Compare: projections, matchups, recent form
  • Rank by: Ceiling > Floor > Consistency
Step 3: Defense Evaluation

Use the defense-streaming-analyst subagent to:

  • Compare current DEF projection vs top 3 available
  • Get clear recommendation: STREAM / HOLD / CONSIDER
  • Include specific streaming options with projections

Always evaluate defense streaming - it's free points on the table.

Read the full file on GitHub · 122 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. 9d ago First seen · 122 lines · 0 tokens per session scan A 62296602ae12

Subscribe to this mod's changes

startsit is a command published in the GitHub repository GregBaugues/tokenbowl-mcp (6 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 913 tokens. 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.