scope

scope is a command for coding agents from allsmog/vuln-scout. It costs 21 tokens per session (7,976 once invoked), scanned A, original, MIT.

A command for preparing a focused snapshot of a large codebase for later security review. A monorepo is one repository containing multiple related applications or packages.

In plain words
What is it for?
Use it to list packages in a monorepo, include or exclude files, compress code by language, and save a scope for threat modeling or security analysis. The original source is still used when running static scanners.
Why use it?
Large repositories can contain more code than a reviewer can inspect at once. This command helps select relevant files, identify workspace structure, and create a manageable review snapshot.

Command

Part of the vuln-scout plugin — 32 skills, 15 commands, 9 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/allsmog/vuln-scout/scope
Clone the repo
git clone --depth 1 https://github.com/allsmog/vuln-scout

Or install vuln-scout, the plugin that ships this one along with the rest of its 32 skills, 15 commands, 9 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 scope

README.md
[![agentmods](https://agentmods.dev/badge/commands/allsmog/vuln-scout/scope.svg)](https://agentmods.dev/commands/allsmog/vuln-scout/scope)
Your own site
<a href="https://agentmods.dev/commands/allsmog/vuln-scout/scope"><img src="https://agentmods.dev/badge/commands/allsmog/vuln-scout/scope.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,976 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 $0.00021 $0.07976
Opus 5 $0.00010 $0.03988
Sonnet 5 $0.00004 $0.01595
Haiku 4.5 $0.00002 $0.00798

Measured 5d ago against content hash 1cb9407ada6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scope 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 5d 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.

vuln-scout/commands/scope.md · 787 lines

How it starts

The opening of the file, as written. The whole thing — 787 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scope Command - Prepare Focused Analysis

Prepare a focused analysis scope for large codebases or monorepos using repomix. Creates a digestible snapshot of the target code for subsequent security analysis.

Saved scope files are context artifacts for Claude-side review and threat modeling. Static tool entrypoints like scan_orchestrator.py still run against the original source directory or workspace, not the generated markdown snapshot.

Flags

Flag Effect
--list List workspaces/packages in monorepo with size estimates
--compress Use language-aware compression (Go: 97%, TS/JS: 80%)
--include Glob patterns to include
--exclude Glob patterns to exclude
--name Output filename (default: derived from path)
--force Force scope even if >300k tokens
--language Force specific language strategy (go|ts|py|java|rust|php|cs|ruby|sol)

List Workspaces (--list)

When --list is provided, detect and display monorepo structure:

/vuln-scout:scope --list

Detects:

  • npm/yarn/pnpm workspaces (package.json, pnpm-workspace.yaml)
  • Go modules (go.work, multiple go.mod)
  • Maven/Gradle modules (pom.xml, settings.gradle)
  • Rust workspaces (Cargo.toml)
  • Python packages (pyproject.toml, setup.py)

Output:

## Detected Workspaces

| Name | Path | Language | Est. Tokens | Risk |
|------|------|----------|-------------|------|
| query-service | query-service/ | Go | 184k | HIGH |
| index-service | index-service/ | Go | 100k | HIGH |
| tahoma | tahoma/ | Go | 706k | MEDIUM |

### Recommendations
- query-service: `/scope query-service --name qs`
- tahoma is oversized: scope sub-directories individually

Polyglot Monorepo Detection (Automatic)

When --list is used, polyglot detection happens automatically. Mixed-language codebases are identified and services are mapped to their languages:

/vuln-scout:scope --list

Step 1: Detect All Languages

Read the full file on GitHub · 787 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. 5d ago First seen · 787 lines · 21 tokens per session scan A 1cb9407ada6e

Subscribe to this mod's changes

scope is a command published in the GitHub repository allsmog/vuln-scout (24 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 7,976 once invoked, about $0.0001 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 2026-08-30.