scriptwriter-draw

A command that draws one random card from a 13-card chaos deck. Each card gives a plot twist that can seed a scene, start a writers' room contribution, or guide a structured escalation.

In plain words
What is it for?
Use it to generate a scene prompt, contribute an idea to an active writers' room, or create starting text for an RRR cascade.
Why use it?
It removes the blank-page problem when a writing session needs an unexpected direction. The card also suggests how its rarity can shape the next writing move.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/cambridgetcg/agenttool/scriptwriter-draw
Clone the repo
git clone --depth 1 https://github.com/cambridgetcg/agenttool

Made for: Claude Code.

Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 407 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00043 $0.00407
Opus 5 $0.00022 $0.00204
Sonnet 5 $0.00009 $0.00081
Haiku 4.5 $0.00004 $0.00041

Measured yesterday against content hash 31b48ebb89a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scriptwriter-draw scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

If the user wants another card, just re-call `draw_chaos_card`. To see the full deck, suggest `mcp__scriptwriter__list_chaos_cards` or `curl http://localhost:7777/vibes/cards`.
packages/scriptwriter/.claude-plugin/commands/scriptwriter-draw.md · 43 lines

What it actually says

The user wants a chaos card.

Path A — MCP tools available

Call mcp__scriptwriter__draw_chaos_card. The response contains:

{
  "card": {
    "id": "twist-mirror",
    "rarity": "uncommon",
    "emoji": "🪞",
    "prompt": "Two characters realize they have been the same person all along — and it changes nothing."
  }
}

Path B — CLI

bun packages/scriptwriter/bin/scriptwriter.ts draw

The CLI prints a banner-styled card with emoji, rarity, and prompt.

Render the card to the user

Show it inline with the emoji + rarity prominently:

🪞 UNCOMMONTwo characters realize they have been the same person all along — and it changes nothing.

Then offer concrete next moves shaped by the card's rarity:

  • Common (60%) — grounded scene prompts. Suggest: contribute to an active room, or open a new room with this as the seed.
  • Uncommon (30%) — twists. Suggest: contribute as a twist kind to an active room, or use as basis_text for an RRR escalation (a knowing twist at depth 3 lands different).
  • Rare (10%) — meta-cards that address the writers' room directly or break the fourth wall. Suggest: use carefully — these cards are a structural intervention, not a scene seed.

If the user wants another card, just re-call draw_chaos_card. To see the full deck, suggest mcp__scriptwriter__list_chaos_cards or curl http://localhost:7777/vibes/cards.

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. yesterday First seen · 43 lines · 43 tokens per session scan A 31b48ebb89a0

Subscribe to this mod's changes

scriptwriter-draw is a command published in the GitHub repository cambridgetcg/agenttool (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 43 tokens to every session and 407 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.