agentmods.dev

storm-write

storm-write is a skill for Claude Code from FradSer/dotclaude. It costs 59 tokens per session (636 once invoked), scanned A, original, MIT.

A writing tool for phase three of the STORM research-and-writing process. It turns a prepared outline and research sources into article sections with inline citations, which are source markers inside the text.

In plain words
What is it for?
Use it to write the body of a researched article section by section, using the relevant sources for each section and leaving introduction, conclusion, and summary placeholders for later.
Why use it?
It removes the need to draft every section manually and keeps the writing grounded in the sources gathered earlier.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Part of the storm plugin — 5 skills, 1 agent shipped together

not rated 593repo 7d ago A scan 59 tokens original MIT

Good fit Use it to write the body of a researched article section by section, using the relevant sources for each section and leaving introduction, conclusion, and summary placeholders for later.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fradser/dotclaude/write
View source ↗ FradSer/dotclaude dotclaude.frad.me
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 FradSer/dotclaude --skill write
Clone the repo
git clone --depth 1 https://github.com/FradSer/dotclaude

Made for: Claude Code.

Or install storm, the plugin that ships this one along with the rest of its 5 skills, 1 agent.

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 storm-write

README.md
[![agentmods](https://agentmods.dev/badge/skills/fradser/dotclaude/write/github.svg)](https://agentmods.dev/skills/fradser/dotclaude/write)
Your own site
<a href="https://agentmods.dev/skills/fradser/dotclaude/write"><img src="https://agentmods.dev/badge/skills/fradser/dotclaude/write/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 storm-write

Your own site · 80×15
<a href="https://agentmods.dev/skills/fradser/dotclaude/write"><img src="https://agentmods.dev/badge/skills/fradser/dotclaude/write.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 636 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 $0.00059 $0.00636
Opus 5.5 $0.00024 $0.00254
Sonnet 5.5 $0.00012 $0.00127
Haiku 4.5 $0.00006 $0.00064

Measured 22d ago against content hash ee7056cbb259, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

storm-write 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 22d 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.

storm/skills/write/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/storm:write

Phase 3 of the STORM pipeline. Writes each outline section in parallel (one Task subagent per section), each grounded in top-k relevant sources from the research information table, with inline [n] citations.

CRITICAL: Prerequisites

  • Load storm-engine via the Skill tool.
  • outline.md MUST exist (phase 2 complete). If absent, stop and instruct the user to run /storm:outline first.

Completion Contract

This phase is complete iff article.md exists and every outline section (except Introduction/Conclusion/Summary placeholders) has body text. If --force is not set and it exists, skip and exit early.

Procedure

  1. Resolve output dir.
  2. Read outline.md and research/sources.json. Index sources for retrieval (simple: rank by keyword/heading overlap with the section title).
  3. Identify sections to write — skip any whose heading is exactly "Introduction", "Conclusion", or "Summary" (these are filled in polish).
  4. Parallel writing — for each section, launch ONE Task subagent (single message, parallel). Each subagent:
    • Receives: topic, section heading, top-k relevant sources (default --retrieve-top-k 3), the full outline for context.
    • Writes the section body with inline [n] citations mapping to sources.json ids.
    • If no relevant sources, writes uncited and marks <!-- TODO: no source -->.
    • Returns the section markdown.
  5. Assemble — concatenate sections in outline order under their headings into article.md. Preserve the heading hierarchy from outline.md.
  6. Verify every non-placeholder section has body. Update run-config.json: phases.write = "completed", section count, any TODO-flagged sections.

Citation Rules

  • Only cite [n] where n is an existing id in sources.json. Never mint a new id here.
  • Place [n] immediately after the claim it supports. Multi-source claims use [1][2].
  • Do not cite in placeholder sections.

Output

Report: number of sections written, number of citations used, list of sections flagged as TODO (no source), and the path to article.md.

Read the full file on GitHub · 44 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. 22d ago First seen · 44 lines · 59 tokens per session scan A ee7056cbb259

Subscribe to this mod's changes

storm-write is a skill published in the GitHub repository FradSer/dotclaude (593 stars, last pushed 7d ago), licensed MIT. It adds 59 tokens to every session and 636 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-24.

ResearchWriting and docsclaude
Related

Other skills, from other repositories

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

systematic-debugging

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

obra/superpowers · 21 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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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