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.
npx agentmods add commands/nasrulhazim/claude/outputgit clone --depth 1 https://github.com/nasrulhazim/claudeWrote 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.
[](https://agentmods.dev/commands/nasrulhazim/claude/output)<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>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.
| Model | Per session | Once 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 |
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.
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
- If
$ARGUMENTSnames a mode, adopt it for the remainder of the session and confirm in one line. - If
$ARGUMENTSis empty, report the current mode and list the available ones. - If
$ARGUMENTSisresetordefault, 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,
tldrandjsonincluded. verboseis not permission to pad. More detail, not more words per point.tldris 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.
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.
- yesterday First seen · 41 lines · 31 tokens per session scan A 4f5798942fea
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.