diagnose-draft

diagnose-draft is a skill for Claude Code from OC-NeuralSense/reader-first-writing-skills. It costs 188 tokens per session (2,222 once invoked), scanned A, original, Apache-2.0.

A diagnostic skill for identifying problems in a draft without rewriting it. It separates structural faults, such as ordering and grouping, from prose faults, such as sentence-level issues.

In plain words
What is it for?
Use it to find and locate faults in a document, including problems with its main question, structure, logic, wording, or clarity.
Why use it?
It gives the writer a precise problem report while preserving the draft for later decisions about how to fix it.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the reader-first-writing plugin — 12 skills, 3 agents shipped together

Good fit Use it to find and locate faults in a document, including problems with its main question, structure, logic, wording, or clarity.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add OC-NeuralSense/reader-first-writing-skills
Claude Code
/plugin install reader-first-writing

Made for: Claude Code.

Or install reader-first-writing, the plugin that ships this one along with the rest of its 12 skills, 3 agents.

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 diagnose-draft

README.md
[![agentmods](https://agentmods.dev/badge/skills/oc-neuralsense/reader-first-writing-skills/diagnose-draft/github.svg)](https://agentmods.dev/skills/oc-neuralsense/reader-first-writing-skills/diagnose-draft)
Your own site
<a href="https://agentmods.dev/skills/oc-neuralsense/reader-first-writing-skills/diagnose-draft"><img src="https://agentmods.dev/badge/skills/oc-neuralsense/reader-first-writing-skills/diagnose-draft/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 diagnose-draft

Your own site · 80×15
<a href="https://agentmods.dev/skills/oc-neuralsense/reader-first-writing-skills/diagnose-draft"><img src="https://agentmods.dev/badge/skills/oc-neuralsense/reader-first-writing-skills/diagnose-draft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 188 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,222 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 $0.00188 $0.02222
Opus 5 $0.00094 $0.01111
Sonnet 5 $0.00038 $0.00444
Haiku 4.5 $0.00019 $0.00222

Measured 10d ago against content hash 8e8185f7008f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

diagnose-draft 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 10d 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/diagnose-draft/SKILL.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

diagnose-draft

Purpose

Find what is wrong with a draft and say so precisely, without fixing anything. Diagnosis produces a report, not a rewrite. The value is a map of faults the writer can weigh and route -- a value that is destroyed the moment a diagnostic pass starts silently editing.

When to use

  • The user wants to know the faults in a draft and where they are.
  • "This reads off", "what's wrong here", "list the problems".

When NOT to use

  • A fast surface pass that also applies fixes -> quick-pass workflow.
  • The user wants the fixes made, not found -> revise-structure / revise-prose.
  • The user wants a release go/no-go -> review-document (audit depth).

Inputs

  • The draft (complete or partial).
  • reader-frame contract (the audience model every judgment reads from).

Two layers, never merged

Report faults on two distinct layers and never list a finding from one beside a finding from the other as the same kind of problem:

  • Structural layer -- the architecture: governing question, grouping, ordering, and whether each parent is honestly earned by its children. These are faults of arrangement and logic.
  • Prose layer -- the sentences and paragraphs: parsing, recoverable coherence, unambiguous reference, concreteness, and bloat/thinness. These are faults of surface rendering.

Merging the two hides the single distinction that most determines what to do next.

Workflow

  1. Read the reader-frame; every "is this clear / is this supported" judgment is made against this reader, not an abstract one.
  2. Structural audit (run the outline-validator indicators): check for a missing or wrong governing question, ungrouped or empty-topper groupings, a buried answer, mixed within-group ordering, orphan claims, and any parent that its children do not actually establish.
  3. Prose audit (run the prose-analyzer indicators): check for unrecoverable coherence between adjacent sentences, misparse traps and deep center-embedding, ambiguous reference, abstraction that cannot be pictured, and genuine wordiness or thinness.
  4. For each fault, write a finding: a location anchor plus the concrete test it failed. "This is unclear" is a complaint, not a finding.
  5. Set severity: blocking (must be gone before release) vs non-blocking.
  6. Note coverage per layer and, for quick depth, mark the report non-exhaustive.
  7. Emit the defect-report file. Do not touch the draft.

Read the full file on GitHub · 186 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. 10d ago First seen · 186 lines · 188 tokens per session scan A 8e8185f7008f

Subscribe to this mod's changes

diagnose-draft is a skill published in the GitHub repository OC-NeuralSense/reader-first-writing-skills (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 188 tokens to every session and 2,222 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

provider-integration

Adds new AI providers to claude-council, configures provider API settings, troubleshoots provider connections, and documents the provider script interface. Covers creating provider shell scripts, setting API keys, and validating connectivity. Triggers on "add provider", "new AI agent", "provider not working", "API…

hex/claude-council · 74 tokens

update-lid

Configure or reconcile a project for linked-intent development (LID). Dispatches on project state — fresh bootstrap, append directives to an existing agent-instructions file (AGENTS.md or CLAUDE.md), add missing mode marker, reconcile convention drift, or run mode transitions. Invoked as /update-lid. For fresh…

jszmajda/lid · 105 tokens

arrow-maintenance

Navigation and audit overlay for linked-intent development. Use when working with docs/arrows/ — orienting via index.yaml, auditing spec-to-code coherence, detecting reverse orphans and drift, splitting/merging/renaming/re-parenting segments. Dual-mode: ambient guidance when the overlay is present…

jszmajda/lid · 85 tokens

map-codebase

Bootstrap LID in an existing (brownfield) codebase. Deep-reads every file in the declared scope, offers lens-based clustering options, generates skeleton LLDs/HLD/EARS bottom-up, then creates arrow docs and prompts the user to flesh out the skeletons. Token-intensive by design. Use when asked to map a codebase…

jszmajda/lid · 92 tokens

design

Create a doc-as-code design package from a PRD or SPEC. Conditionally generates C4 diagrams (Context/Container/Component), sequence diagrams, ER diagram + Data Dictionary, OpenAPI 3.0, AsyncAPI 3.0, ADRs, domain glossary, state diagrams, and deployment view as Mermaid-rendered Markdown files. Use when PM mentions…

cryndoc/polisade-orchestrator · 162 tokens

superbrain-distill

Internal SuperBrain skill — run by the detached capture child to distill a session-event delta into routed Obsidian notes. Not for direct user invocation.

m3talux/superbrain · 36 tokens