write-rescue

write-rescue is a command for coding agents from animalzinc/claude-plugins. It costs 0 tokens per session (933 once invoked), scanned A, original, MIT.

A diagnostic command for an existing draft, outline, or notes that are not working, preparing them for a separate structured writing command.

In plain words
What is it for?
Reviewing writing materials, classifying what is present, and mapping gaps to the stages of a writing process.
Why use it?
It identifies missing or weak parts before revision begins, such as the main idea, structure, research, introduction, or draft.

Command

Part of the structured-article-writer plugin — 3 commands shipped together

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/animalzinc/claude-plugins/write-rescue
Clone the repo
git clone --depth 1 https://github.com/animalzinc/claude-plugins

Or install structured-article-writer, the plugin that ships this one along with the rest of its 3 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 write-rescue

README.md
[![agentmods](https://agentmods.dev/badge/commands/animalzinc/claude-plugins/write-rescue.svg)](https://agentmods.dev/commands/animalzinc/claude-plugins/write-rescue)
Your own site
<a href="https://agentmods.dev/commands/animalzinc/claude-plugins/write-rescue"><img src="https://agentmods.dev/badge/commands/animalzinc/claude-plugins/write-rescue.svg" alt="Measured on agentmods" 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 933 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.00933
Opus 5 $0.00000 $0.00466
Sonnet 5 $0.00000 $0.00187
Haiku 4.5 $0.00000 $0.00093

Measured 4d ago against content hash 46a14418f881, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write-rescue 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 4d 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.

plugins/structured-article-writer/commands/write-rescue.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/write-rescue

Diagnose an existing draft or outline that isn't working, map it against the structured writing process, and set it up so /write can take over.

Arguments

$ARGUMENTS — Required: path to the existing draft, outline, or notes. Can be a file path or a slug for an existing article folder.

Core rules

  1. Read everything first. Don't diagnose until you've read all provided material completely.
  2. Be honest. If the piece has problems, name them clearly.
  3. Don't fix yet. This command diagnoses. /write fixes.
  4. DO NOT use AskUserQuestion. Use plain text prompts for natural conversation.

Process

Step 1: Read and assess

Read the provided material completely. Classify what exists:

Element Status
Thesis (stated or implied) EXISTS / WEAK / MISSING
Earned secret EXISTS / WEAK / MISSING
Structure (outline or headers) EXISTS / WEAK / MISSING
Research (citations, data, examples) EXISTS / WEAK / MISSING
Introduction (hook, sinker, line) EXISTS / WEAK / MISSING
Draft (partial or complete) EXISTS / WEAK / MISSING

Step 2: Map to process phases

Present a diagnostic table:

[DIAGNOSIS]

Phase Status Evidence
1. Foundation SOLID / WEAK / MISSING What exists or what's absent
2. Thesis SOLID / WEAK / MISSING ...
3. Structure SOLID / WEAK / MISSING ...
4. Research SOLID / WEAK / MISSING ...
5. 30% Outline SOLID / WEAK / MISSING ...
6. Introduction SOLID / WEAK / MISSING ...
7. Draft SOLID / WEAK / MISSING ...
8. Review NOT STARTED ...

Step 3: Identify the failure point

Name the most likely reason the piece isn't working. Common patterns:

  • Thesis drift: Started arguing one thing, ended arguing another. The piece lacks a single through-line.
  • Missing earned secret: The argument is built on recycled advice anyone could write, not on authentic experience.
  • Outline-to-draft jump: Went straight from rough idea to prose, skipping the hard structural thinking. The draft meanders.
  • Research gap: Assertions without evidence. The argument feels thin or unsupported.
  • Hook failure: Generic opening that doesn't grab. No pattern interrupt.
  • 30% overshoot: The outline became a rough draft. Too much detail too early killed the ability to see the structure.
  • Writer-centric structure: Organized by how the writer figured things out, not how the reader needs to receive them.
  • Soft middle: Tried to be both tactical and strategic. Neither lands.

Read the full file on GitHub · 85 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. 4d ago First seen · 85 lines · 0 tokens per session scan A 46a14418f881

Subscribe to this mod's changes

write-rescue is a command published in the GitHub repository animalzinc/claude-plugins (15 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 933 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.