test-argument

test-argument is a skill for Claude Code from OC-NeuralSense/reader-first-writing-skills. It costs 152 tokens per session (1,490 once invoked), scanned A, original, Apache-2.0.

A review skill that checks whether supporting claims actually justify a conclusion. It looks for missing support, irrelevant points, overlap, overclaims, and faulty reasoning.

In plain words
What is it for?
Use it to test argument structures, summaries, and parent-child claim relationships for logical soundness.
Why use it?
It helps distinguish evidence that truly supports an argument from points that only sound related.

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 test argument structures, summaries, and parent-child claim relationships for logical soundness.

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 test-argument

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/oc-neuralsense/reader-first-writing-skills/test-argument"><img src="https://agentmods.dev/badge/skills/oc-neuralsense/reader-first-writing-skills/test-argument.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,490 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 $0.00152 $0.01490
Opus 5 $0.00076 $0.00745
Sonnet 5 $0.00030 $0.00298
Haiku 4.5 $0.00015 $0.00149

Measured 10d ago against content hash 07c8a0724578, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

test-argument 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/test-argument/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

test-argument

Purpose

Judge whether the argument holds: does each parent-child link genuinely follow, and is any support missing, overlapping, or irrelevant? This is an evaluative skill. It reports; it does not rewrite. Its single output is a soundness-layer defect report.

When to use

  • A conclusion plus its support is present and the writer wants it stress-tested.
  • A parent's claim to summarize its children needs checking.

When NOT to use (routing non-triggers)

  • Wants a full draft diagnosis spanning structure and prose -> diagnose-draft.
  • Wants the structure built from scratch -> build-argument.
  • Wants the defects fixed, not just found -> revise-structure.

Inputs

  • argument-blueprint contract, OR conclusion_plus_claims (required)
  • reader-frame contract (optional, sharpens relevance judgments)

Workflow

  1. Map the links. Identify every parent-child support relation to be judged.
  2. Judge each link as genuinely following or not; separate logical support from mere rhetorical fit.
  3. Name gaps. Flag missing, overlapping, or irrelevant supports.
  4. Flag defect patterns: overclaims, non-sequiturs, anecdote-treated-as-trend, false dichotomy.
  5. Require a completeness note per group; flag any group lacking one.
  6. Emit the defect report; on deep depth, reconcile against an independent reviewer's findings first.

Decision rules

  • A true-but-irrelevant support is not load-bearing; say so.
  • Rhetorical fit never substitutes for logical support.
  • Each finding cites a location and the concrete test it failed.
  • Report only; propose fixes as recommendations, never applied edits.

Output contract

Produces a defect-report on the soundness layer (see architecture/handoff-contracts.yaml): findings with location, failed_test, severity, evidence, and recommended_fix; set coverage.soundness = true and exhaustiveness. Route via recommended_next_step (usually revise-structure).

Every run also attaches a decision_record: the exact methodology/<file>.md#<section> references consulted (drawn from References to load below), the checks performed, any rule set aside naming its lawful exception, warnings, unresolved questions, and status. This cites the project's own methodology only, visible by default, never the source books.

Read the full file on GitHub · 138 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 · 138 lines · 152 tokens per session scan A 07c8a0724578

Subscribe to this mod's changes

test-argument 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 152 tokens to every session and 1,490 once invoked, about $0.0008 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