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.
git clone --depth 1 https://github.com/josstei/argus-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/josstei/argus-claude/config)<a href="https://agentmods.dev/commands/josstei/argus-claude/config"><img src="https://agentmods.dev/badge/commands/josstei/argus-claude/config/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.
<a href="https://agentmods.dev/commands/josstei/argus-claude/config"><img src="https://agentmods.dev/badge/commands/josstei/argus-claude/config.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00006 | $0.00602 |
| Opus 5.5 | $0.00002 | $0.00241 |
| Sonnet 5.5 | $0.00001 | $0.00120 |
| Haiku 4.5 | $0.00001 | $0.00060 |
Grade A, and why
config 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Argus Configuration
View review levels and manage global settings.
Arguments: $ARGUMENTS
Parse the arguments to determine the action:
| Command | Description |
|---|---|
| (empty) | Show review levels and current settings |
set scope <path> |
Set default scope directory |
set output <format> |
Set default output format |
Review Levels
Argus has three built-in review levels:
| Level | Model | Depth | Description |
|---|---|---|---|
| Fast | Haiku | quick | Quick scan (~2 min, low tokens) |
| Balanced | Sonnet | standard | Standard review (~5 min, moderate tokens) |
| Comprehensive | Opus | thorough | Deep analysis (~8 min, higher tokens) |
Implementation
Step 1: Determine Action
Parse $ARGUMENTS:
- Empty → Show current state
- "set scope <path>" → Set scope
- "set output <format>" → Set output
Step 2: Execute Action
Action: (empty) - Show Configuration
- Load
defaults.jsonto get review levels - Check for scope/output overrides in
~/.claude/argus.json - Detect current scope if set to "auto"
- Display:
Argus Configuration
===================
Review Levels:
fast Haiku | ~2 min
balanced Sonnet | ~5 min (default)
comprehensive Opus | ~8 min
Settings:
scope: {scope_value} {if auto: (currently: detected_path)}
output: {output_value}
Change settings:
/argus:config set scope lib/
/argus:config set output markdown
Action: set scope <path>
- Validate the path is "auto" or exists as a directory
- Write to
~/.claude/argus.json:{ "scope": "lib/" } - Display confirmation:
Set scope = lib/
Valid values: auto, or any valid directory path
Action: set output <format>
- Validate format is one of:
inline,markdown,json - Write to
~/.claude/argus.json:{ "output": "markdown" } - Display confirmation:
Set output = markdown
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.
- 1mo ago First seen · 112 lines · 6 tokens per session scan A 777f3dcb40a9
config is a command published in the GitHub repository josstei/argus-claude (6 stars, last pushed 8mo ago), licensed MIT. It adds 6 tokens to every session and 602 once invoked, about $0.0000 per session on Opus 5.5. 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.
Other commands, from other repositories
create-pr
Create a GitHub pull request from a pushed branch with ticket-aware title and body generation. Not for: committing, pushing, merging, releasing, or editing an existing PR. Output: a dry-run gh pr create command by default, or the created PR URL after explicit execution.
init
Install the formatters this repository needs, with every command visible before it runs.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
extend
Capture a mid-PR sub-idea and implement it onto the current open PR's branch — no new branch, no new PR. Preserves Verify → Review → Deliver.
security-review
Depth-first security audit of the current git diff — OWASP Top 10, secret leakage, insecure-by-default APIs, and language-specific foot-guns. Pass a PR number to audit a specific PR's diff.