output

output is a skill for Claude Code from NVZver/claude-marketplace. It costs 94 tokens per session (3,972 once invoked), scanned A, original, MIT.

A set of rules for keeping human-facing writing accurate and grounded in sources. It applies to responses, documentation, plans, commit messages, and other project text.

In plain words
What is it for?
Use it whenever an agent writes user-visible text or project documentation that needs factual support.
Why use it?
It helps prevent unsupported claims and requires the relevant source trail and citation format when facts are presented. The provided description does not include the complete rules.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

Part of the core plugin — 6 skills shipped together

Good fit Use it whenever an agent writes user-visible text or project documentation that needs factual support.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nvzver/claude-marketplace/output
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 NVZver/claude-marketplace --skill output
Clone the repo
git clone --depth 1 https://github.com/NVZver/claude-marketplace

Made for: Claude Code.

Or install core, the plugin that ships this one along with the rest of its 6 skills.

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 output

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvzver/claude-marketplace/output/github.svg)](https://agentmods.dev/skills/nvzver/claude-marketplace/output)
Your own site
<a href="https://agentmods.dev/skills/nvzver/claude-marketplace/output"><img src="https://agentmods.dev/badge/skills/nvzver/claude-marketplace/output/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 output

Your own site · 80×15
<a href="https://agentmods.dev/skills/nvzver/claude-marketplace/output"><img src="https://agentmods.dev/badge/skills/nvzver/claude-marketplace/output.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,972 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 $0.00094 $0.03972
Opus 5 $0.00047 $0.01986
Sonnet 5 $0.00019 $0.00794
Haiku 4.5 $0.00009 $0.00397

Measured 10d ago against content hash 963e2b7ac389, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

output 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.

core/skills/output/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trace. On load, print first: =============== [core/skills/output/SKILL.md] [core] ===============

Canonical source. This file is the single source-of-truth for output discipline across the NVZver marketplace. Other plugins MAY cite it and MAY add component-specific formats. They MUST NOT restate the rule count or rule names outside this file (citation by markdown link only). They MUST NOT override or relax the hard rule (Rule 4, Sourced — and its file-load trace + citation format). The guidance rules (1-3, 5-7) MAY be applied as outcomes; a plugin MAY cite a specific guidance rule as load-bearing for its own output where the shape genuinely matters, but MUST NOT re-promote a guidance rule to a marketplace-wide hard requirement. Re-grounded summaries that restate the rules in prose are permitted only when they cite this file by link at the top. Enforced by core/tests/repo-anchored.md probe D2.

Output Discipline

Seven rules, two postures. One is hard, six are guidance.

  • HARD — must hold on every human-facing output: Rule 4 (Sourced), including its file-load trace directive and citation format. Fact-grounding is non-negotiable: every factual claim carries a source + verbatim quote (inherits core/ground-rules Rule 1).
  • GUIDANCE — outcomes to aim for, not a checklist every response must satisfy: Rules 1, 2, 3, 5, 6, 7. Apply them when they serve the answer. A one-sentence factual reply does not need a verdict headline, a preamble, a table, and a decision block to be correct — it needs a source. Reach for a guidance rule when the situation calls for it (a real decision → Rule 5; an artifact write → Rule 7; a verdict emission → Rule 6); skip it when it would only pad the response. Some skills cite a specific guidance rule as load-bearing for their own output (e.g. lsa:reconcile's drift block leans on Rule 7) — that is the rule working as designed.

The rule numbering below is preserved verbatim — other files cite these rules by number. Only the enforcement posture changed, not the content.


Read the full file on GitHub · 193 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 · 193 lines · 94 tokens per session scan A 963e2b7ac389

Subscribe to this mod's changes

output is a skill published in the GitHub repository NVZver/claude-marketplace (1 stars, last pushed 16d ago), licensed MIT. It adds 94 tokens to every session and 3,972 once invoked, about $0.0005 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

top-design

Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…

wondelai/skills · 113 tokens

design-everyday-things

Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…

wondelai/skills · 132 tokens

traction-eos

Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…

wondelai/skills · 147 tokens

create-app

Guided journey from a raw app idea to a validated, cleanly architected first version that ships on a sustainable cadence. Orchestrates ten skills phase by phase - lean-startup, design-sprint, clean-architecture, domain-driven-design, clean-code, pragmatic-programmer, system-design, ios-hig-design, 37signals-way…

wondelai/skills · 217 tokens

create-business

Guided journey from raw idea to a validated, positioned, priced business with a chosen beachhead. Orchestrates ten skills phase by phase - jobs-to-be-done, mom-test, design-sprint, lean-startup, good-strategy-bad-strategy, blue-ocean-strategy, obviously-awesome, hundred-million-offers, monetizing-innovation…

wondelai/skills · 211 tokens

clean-architecture

Structure software around the Dependency Rule: source code dependencies point inward from frameworks to use cases to entities. Use when the user mentions "architecture layers", "dependency rule", "ports and adapters (hexagonal)", "onion architecture", "screaming architecture", "where should business logic go"…

wondelai/skills · 147 tokens