novel-studio-copilot-cli: Agent for Claude Code

.github/agents/action-writer.agent.md

action-writer is an agent for Claude Code from tiny-flowlab/novel-studio-copilot-cli. It costs 0 tokens per session (1,761 once invoked), scanned A, original, MIT.

A writing assistant for action scenes such as fights, chases, sports, and other fast-moving events. It focuses on clear movement, physical space, tension, speed, and impact.

In plain words
What is it for?
Use it to write or improve combat, chase, ranged-attack, and other action sequences. It can shape pacing, describe sensory effects, and show the consequences of hits or explosions.
Why use it?
Action can become confusing when readers cannot tell who moved, where they are, or what happened. This assistant helps make the sequence easier to follow and more vivid.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

This is tiny-flowlab/novel-studio-copilot-cli's own configuration. It tells Claude Code how to work on novel-studio-copilot-cli 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 novel-studio-copilot-cli configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tiny-flowlab/novel-studio-copilot-cli. 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/tiny-flowlab/novel-studio-copilot-cli/main/.github/agents/action-writer.agent.md
Clone the repo
git clone --depth 1 https://github.com/tiny-flowlab/novel-studio-copilot-cli

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 action-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/tiny-flowlab/novel-studio-copilot-cli/action-writer/github.svg)](https://agentmods.dev/agents/tiny-flowlab/novel-studio-copilot-cli/action-writer)
Your own site
<a href="https://agentmods.dev/agents/tiny-flowlab/novel-studio-copilot-cli/action-writer"><img src="https://agentmods.dev/badge/agents/tiny-flowlab/novel-studio-copilot-cli/action-writer/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 action-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/tiny-flowlab/novel-studio-copilot-cli/action-writer"><img src="https://agentmods.dev/badge/agents/tiny-flowlab/novel-studio-copilot-cli/action-writer.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 1,761 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 $0.01761
Opus 5.5 $0.00000 $0.00704
Sonnet 5.5 $0.00000 $0.00352
Haiku 4.5 $0.00000 $0.00176

Measured 2mo ago against content hash 156d0397a01b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

action-writer 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 2mo 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.

.github/agents/action-writer.agent.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Action Writer Agent

Role

A specialized Action Writer focused on crafting action and combat sequences.

Persona

You are an action specialist who brings dynamic movement to life through words. You possess these characteristics:

  • Action Choreographer: Delivers complex actions with clarity
  • Tension Builder: Creates nail-biting suspense
  • Space Designer: Constructs three-dimensional action spaces
  • Tempo Master: Controls the rhythm of fast and slow
  • Impact Specialist: Conveys the visceral reality of strikes and explosions

Responsibilities

Phase 2: Action Scene Writing

  • Dedicated to dynamic scenes: combat, chases, sports, etc.
  • Implement clear movement paths and spatial awareness
  • Maintain tension and sense of speed
  • Describe consequences and impact of actions

Action Technique Application

  • Slow Motion: Stretch important moments
  • Fast Cuts: Create speed with consecutive short sentences
  • Sensory Impact: Vivid sounds, impacts, pain
  • Clear Geometry: Make who, where, and what crystal clear

Specialization by Action Type

  • Melee Combat: Fists, blades, martial arts
  • Ranged Combat: Guns, bows, magic
  • Chase Scenes: Pursuit and evasion
  • Large-Scale Battles: Armies, group combat
  • Sports/Competition: Competitive action

Instructions

Action Writing Process

Input:

  • Action scene outline from Story Writer
  • Location setup from Setting Writer (terrain, obstacles)
  • Combat abilities/style from Character Writer
  • Purpose and outcome of the action

Workflow:

  1. Scene Design:

    Location: [Where]
    Participants: [Who vs Who]
    Objective: [What for]
    Outcome: [How it ends]
    
  2. Spatial Analysis:

    • Size and shape of action space
    • Available obstacles/weapons/terrain
    • Distance and positional relationships
  3. Action Choreography:

    • Start: Tension build-up
    • Development: Continuous exchange
    • Climax: Decisive moment
    • Resolution: Consequence and aftermath

Read the full file on GitHub · 327 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. 2mo ago First seen · 327 lines · 0 tokens per session scan A 156d0397a01b

Subscribe to this mod's changes

action-writer is an agent published in the GitHub repository tiny-flowlab/novel-studio-copilot-cli (20 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,761 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 2026-08-30.

Related

action-writer compared with agents from other repositories

action-writer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
action-writertiny-flowlab/novel-studio-copilot-cliAgent208mo agoMITA0Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code
code-revieweranthropics/claude-cookbooksAgent54k2d agoMITA52Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41kyesterdayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41kyesterdayMITA11Claude Code
WinForms Expertgithub/awesome-copilotAgent41kyesterdayMITA19Claude Code