help

help is a command for coding agents from josstei/argus-claude. It costs 7 tokens per session (493 once invoked), scanned A, original, MIT.

A help command for Argus, a code-review tool. It explains the available review, configuration, and help commands, including their options.

In plain words
What is it for?
Use it to view a command overview, common workflows, or configuration guidance.
Why use it?
It lets you check the correct command and settings without remembering Argus's syntax.

Command

Part of the argus plugin — 4 commands, 1 agent 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/josstei/argus-claude/help
Clone the repo
git clone --depth 1 https://github.com/josstei/argus-claude

Or install argus, the plugin that ships this one along with the rest of its 4 commands, 1 agent.

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 help

README.md
[![agentmods](https://agentmods.dev/badge/commands/josstei/argus-claude/help.svg)](https://agentmods.dev/commands/josstei/argus-claude/help)
Your own site
<a href="https://agentmods.dev/commands/josstei/argus-claude/help"><img src="https://agentmods.dev/badge/commands/josstei/argus-claude/help.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 493 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 $0.00007 $0.00493
Opus 5 $0.00003 $0.00246
Sonnet 5 $0.00001 $0.00099
Haiku 4.5 $0.00001 $0.00049

Measured 3d ago against content hash 09db317876da, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

help 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 3d 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.

commands/help.md · 93 lines

What it actually says

Argus Help

Display help information based on arguments.

Arguments: $ARGUMENTS

Argument Shows
(empty) Command overview
workflows Common workflow examples
config Configuration options

Output

Default (no argument)

Argus Commands
==============

Review:
  /argus:review              Run code review
  /argus:review --level X    Use level (fast/balanced/comprehensive)
  /argus:review --scope X    Review specific directory
  /argus:review --output X   Set output (inline/markdown/json)
  /argus:review --external   Enable external validators (detected tools only)
  /argus:review --yes        Accept defaults, no prompt

Config:
  /argus:config              View settings
  /argus:config set scope X  Set default scope
  /argus:config set output X Set default output

Other:
  /argus:help                This help
  /argus:help workflows      Common workflow examples
  /argus:welcome             Show welcome message

workflows

Common Workflows
================

Quick check before commit:
  /argus:review --level fast

Full review for PR:
  /argus:review --level comprehensive

Focus on specific area:
  /argus:review --scope features/auth/

Accept defaults immediately:
  /argus:review --yes

Save report to file:
  /argus:review --output markdown

Cross-validate with external tools (detected only):
  /argus:review --external

config

Configuration Options
=====================

Settings:
  scope       auto, src/, lib/, path  (default: auto)
  output      inline, markdown, json  (default: inline)

Review Levels:
  fast          Haiku | ~2 min | Quick scan
  balanced      Sonnet | ~5 min | Standard review (default)
  comprehensive Opus | ~8 min | Deep analysis

Examples:
  /argus:config set scope src/
  /argus:config set output markdown

Config file:
  User: ~/.claude/argus.json (personal)
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. 3d ago First seen · 93 lines · 7 tokens per session scan A 09db317876da

Subscribe to this mod's changes

help is a command published in the GitHub repository josstei/argus-claude (6 stars, last pushed 6mo ago), licensed MIT. It adds 7 tokens to every session and 493 once invoked, about $0.0000 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.