agent-scope

agent-scope is a skill for Claude Code, Codex from floomhq/moto. It costs 0 tokens per session (814 once invoked), scanned A, original, MIT.

A scope guard for AI coding agents: a tool that limits which files an agent may change while allowing it to read the wider project. A monorepo is one repository containing multiple applications or packages.

In plain words
What is it for?
Use it to define allowed and protected paths, request approval before protected edits, check a change set, and add CI checks that catch scope violations.
Why use it?
It helps prevent an agent working on one task from accidentally changing unrelated areas such as authentication, billing, or database migrations.

Skill for Claude CodeCodex

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 skills/floomhq/moto/agent-scope
Any agent
npx skills add floomhq/moto --skill agent-scope
Clone the repo
git clone --depth 1 https://github.com/floomhq/moto

Made for: Claude Code, Codex.

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 agent-scope

README.md
[![agentmods](https://agentmods.dev/badge/skills/floomhq/moto/agent-scope.svg)](https://agentmods.dev/skills/floomhq/moto/agent-scope)
Your own site
<a href="https://agentmods.dev/skills/floomhq/moto/agent-scope"><img src="https://agentmods.dev/badge/skills/floomhq/moto/agent-scope.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 814 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 $0.00000 $0.00814
Opus 5 $0.00000 $0.00407
Sonnet 5 $0.00000 $0.00163
Haiku 4.5 $0.00000 $0.00081

Measured 4d ago against content hash 8066cd8599ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-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 4d 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.

claude/skills/agent-scope/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.



name: agent-scope description: | Enforce scoped write access for AI coding agents. Use when starting a new task, before committing changes, when asked to "check scope", "validate my diff", "did I touch anything I shouldn't", or when working in a monorepo where protected modules (auth, billing, migrations) must not be silently modified.

agent-scope — Scope Guard for AI Coding Agents

agent-scope stops AI agents from silently changing code outside their intended task.

  • Read broadly (**/*)
  • Write narrowly (scoped paths)
  • Ask before touching protected code
  • Run checks before finishing

When to use

  • Starting a new task in a monorepo
  • Agent keeps touching unrelated modules
  • Need to lock auth, billing, or database layers
  • Want a CI gate that catches scope violations in PRs

Quick setup

npm install -g agent-scope
agent-scope init

Edit agent.scope.yml:

version: "0.1"
mode: strict

task:
  id: "your-task-id"
  title: "Your task title"

scope:
  read:
    - "**/*"
  write:
    - "apps/web/settings/**"
    - "packages/email/**"
    - ".agent-scope/**"
  protected:
    - "packages/auth/**"
    - "packages/billing/**"
    - "db/migrations/**"
  approval_required:
    - "package.json"
    - "pnpm-lock.yaml"

Daily workflow

Before editing

Review agent.scope.yml to confirm your write boundaries.

After editing

agent-scope check

If violations appear, do not proceed. Your options:

  1. Revert the out-of-scope changes
  2. Request scope expansion:
    agent-scope request packages/auth/session.ts \
      --reason "Need to expose email preference in session"
    
  3. Approve if human already gave permission:
    agent-scope approve packages/auth/session.ts
    

Before finishing

agent-scope run

This validates scope and then runs checks.before_done from the config.

Integration with agents

Claude Code hook

Add to your workflow:

Read the full file on GitHub · 147 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. 4d ago First seen · 147 lines · 0 tokens per session scan A 8066cd8599ae

Subscribe to this mod's changes

agent-scope is a skill published in the GitHub repository floomhq/moto (32 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 814 tokens. 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.

Related

Other skills, from other repositories

issue-triage

Issue triage: audit open issues, categorize, detect duplicates, cross-ref PRs, risk assessment, post comments. Args: "all" for deep analysis of all, issue numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.

rtk-ai/rtk · 70 tokens

performance

CLI performance optimization - startup time, memory usage, token savings benchmarking.

rtk-ai/rtk · 13 tokens

build-teaql-app

Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…

teaql/teaql-agent-kit · 112 tokens

moai-kanban-foreman

One unattended kanban foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…

modu-ai/moai-adk · 76 tokens

orchestrator-lanes

Claude Code dev-orchestrator only. File-based multi-lane PM playbook (score, DAG, run-controller, L0/L1/L2, ship). Use when this session IS that agent, or user says info / справка / lane-stack:orchestrator-lanes info. SKIP: Grok, Codex, Kimi, Qwen, AGY, Cursor writer CLIs and any default coding agent — do not load, do…

VKirill/claude-lane-stack · 104 tokens

source-command-methodology-advisor

Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack.

FlorianBruniaux/claude-code-ultimate-guide · 27 tokens