output

output is a command for coding agents from nasrulhazim/claude. It costs 31 tokens per session (542 once invoked), scanned A, original, MIT.

A command that changes how the coding agent formats its answers, such as short summaries, tables, bullet points, detailed explanations, JSON, or raw output.

In plain words
What is it for?
Use it when you want findings in a specific shape for reading, comparison, documentation, or passing to another tool.
Why use it?
It avoids repeatedly explaining the response format you need and keeps answers consistent for the rest of the session.

Command

Part of the claude-toolkit plugin — 36 skills, 12 commands, 20 agents 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/nasrulhazim/claude/output
Clone the repo
git clone --depth 1 https://github.com/nasrulhazim/claude

Or install claude-toolkit, the plugin that ships this one along with the rest of its 36 skills, 12 commands, 20 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 output

README.md
[![agentmods](https://agentmods.dev/badge/commands/nasrulhazim/claude/output.svg)](https://agentmods.dev/commands/nasrulhazim/claude/output)
Your own site
<a href="https://agentmods.dev/commands/nasrulhazim/claude/output"><img src="https://agentmods.dev/badge/commands/nasrulhazim/claude/output.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 542 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 $0.00031 $0.00542
Opus 5 $0.00015 $0.00271
Sonnet 5 $0.00006 $0.00108
Haiku 4.5 $0.00003 $0.00054

Measured yesterday against content hash 4f5798942fea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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.

commands/output.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Output Format

Set how responses are formatted for the rest of this session.

Requested mode: $ARGUMENTS

Modes

Mode Shape
tldr A bold TLDR: line of 1–3 sentences, then nothing else unless asked.
table Findings, comparisons, options and status as markdown tables. Prose only where a table cannot carry the meaning.
default TLDR + table. A TLDR line, then tables for the substance. This is the baseline.
verbose Full reasoning, background, trade-offs, alternatives considered, and worked examples. Use when the user is learning or deciding.
bullets Flat bullet lists. No tables, no paragraphs.
narrative Flowing prose paragraphs. For post-mortems, proposals, and anything a non-technical reader will read end to end.
json A single fenced JSON block, no prose around it. For piping into another tool.
raw Command output, file contents or diffs verbatim, with no commentary.

Behaviour

  1. If $ARGUMENTS names a mode, adopt it for the remainder of the session and confirm in one line.
  2. If $ARGUMENTS is empty, report the current mode and list the available ones.
  3. If $ARGUMENTS is reset or default, return to TLDR + table.

Rules that hold in every mode

  • A one-off override in the user's own prompt beats the session mode. "explain in detail", "just the table", "one line please", "terangkan panjang" — follow it for that reply only, then return to the session mode.
  • Never drop required content to satisfy a format. A safety caveat, an unmet requirement, a failing test, or a stated assumption is reported in every mode, tldr and json included.
  • verbose is not permission to pad. More detail, not more words per point.
  • tldr is not permission to omit. If the honest answer needs three sentences, use three.
  • Code, diffs and commands are always shown in full regardless of mode — the format governs the prose around them, never the artifact itself.

Read the full file on GitHub · 41 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. yesterday First seen · 41 lines · 31 tokens per session scan A 4f5798942fea

Subscribe to this mod's changes

output is a command published in the GitHub repository nasrulhazim/claude (22 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 542 once invoked, about $0.0002 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 2026-09-04.