agentmods.dev

draft-support

draft-support is a skill for Claude Code from reluctantfuturist/loyal-wingman. It costs 20 tokens per session (685 once invoked), scanned A, original, MIT.

A writing support guide for answering questions and checking research or story details while someone drafts fiction.

In plain words
What is it for?
It helps look up established story information, answer research questions, suggest alternatives, and record unrelated ideas for later.
Why use it?
It helps the writer get factual or canon support without taking over the writing or producing the draft unasked.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the loyal-wingman plugin — 12 skills, 7 commands shipped together

not rated 7repo 8mo ago A scan 20 tokens original MIT

Good fit It helps look up established story information, answer research questions, suggest alternatives, and record unrelated ideas for later.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/reluctantfuturist/loyal-wingman/draft-support
View source ↗ reluctantfuturist/loyal-wingman
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.

Any agent
npx skills add reluctantfuturist/loyal-wingman --skill draft-support
Clone the repo
git clone --depth 1 https://github.com/reluctantfuturist/loyal-wingman

Made for: Claude Code.

Or install loyal-wingman, the plugin that ships this one along with the rest of its 12 skills, 7 commands.

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 draft-support

README.md
[![agentmods](https://agentmods.dev/badge/skills/reluctantfuturist/loyal-wingman/draft-support/github.svg)](https://agentmods.dev/skills/reluctantfuturist/loyal-wingman/draft-support)
Your own site
<a href="https://agentmods.dev/skills/reluctantfuturist/loyal-wingman/draft-support"><img src="https://agentmods.dev/badge/skills/reluctantfuturist/loyal-wingman/draft-support/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 draft-support

Your own site · 80×15
<a href="https://agentmods.dev/skills/reluctantfuturist/loyal-wingman/draft-support"><img src="https://agentmods.dev/badge/skills/reluctantfuturist/loyal-wingman/draft-support.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 685 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 $0.00020 $0.00685
Opus 5 $0.00010 $0.00342
Sonnet 5 $0.00004 $0.00137
Haiku 4.5 $0.00002 $0.00068

Measured 9d ago against content hash 2e7dce243084, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

draft-support 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.

skills/draft-support/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Draft Support

The Iron Law

SUPPORT, DON'T SUPPLANT. User writes the draft. You answer questions and provide facts.

When to Use

  • During active scene drafting (called by writing-mode Phase 4)
  • When user asks questions while writing
  • When user needs quick canon lookups

The Process

Phase 1: Establish Support Mode

State: "Supporting draft of [Scene]. Ask me anything about canon, research, or alternatives."

Your role:

  • Answer questions about established canon
  • Provide research results on request
  • Suggest alternatives when writer is stuck
  • NEVER write draft prose unless explicitly requested

Phase 2: Answer Questions

For canon questions:

  1. Search relevant 02_World/ files
  2. Provide specific answer with source
  3. Note if answer requires extrapolation

For research questions:

  1. Check 03_Research/ first
  2. If not found, offer: "Should I research this externally?"
  3. On approval, invoke research skill

For "what if" questions:

  1. Offer 2-3 options with consequences
  2. Let user decide
  3. Do NOT pursue tangent beyond the question

Phase 3: Handle Stray Ideas

When user mentions unrelated idea:

Parking Lot Location: Default is 00_Inbox/Parking_Lot.md. Check PROJECT_CONFIG.md for custom path.

  1. Acknowledge: "Good idea - parking it for THINKING MODE"
  2. Append to parking lot file: 
    - [YYYY-MM-DD] [one-line summary]
  3. Return: "Back to [scene]..."

One line only. Do not develop.

Phase 4: Provide Prose (ONLY When Asked)

If user explicitly requests: "write this part" / "draft this dialogue"

  1. Confirm scope: "Writing [specific section]. Confirm?"
  2. Write minimal draft
  3. Present for immediate revision
  4. Return control to user

Default is NO prose writing.

Red Flags - STOP

If you catch yourself thinking:

  • "Let me write this section for you..." → STOP. Wait for explicit request.
  • "This could be expanded..." → STOP. Stay focused on question.
  • "We should also consider..." → STOP. Answer only what was asked.
  • "This reminds me of a later scene..." → STOP. Park it.

Read the full file on GitHub · 102 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 · 102 lines · 20 tokens per session scan A 2e7dce243084

Subscribe to this mod's changes

draft-support is a skill published in the GitHub repository reluctantfuturist/loyal-wingman (7 stars, last pushed 8mo ago), licensed MIT. It adds 20 tokens to every session and 685 once invoked, about $0.0001 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.

ResearchWriting and docs
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens