repo-scope

repo-scope is a skill for Claude Code from xzawed/claude-grok-build-plugin. It costs 0 tokens per session (755 once invoked), scanned A, original, MIT.

A repository-scope rule for deciding whether this plugin has any remaining work. It treats the documented product scope as complete unless the owner states a new goal.

In plain words
What is it for?
Use it before deciding what to work on next or opening a pull request, especially when reviewing external, manual, deferred, excluded, or newly requested work.
Why use it?
It prevents developers from inventing cleanup or polish tasks and from opening unrequested pull requests.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions Claude Code.

Part of the grok plugin — 4 skills, 27 commands, 1 agent, 1 hook, 1 MCP server shipped together

Good fit Use it before deciding what to work on next or opening a pull request, especially when reviewing external, manual, deferred, excluded, or newly requested work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xzawed/claude-grok-build-plugin/repo-scope
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.

Any agent
npx skills add xzawed/claude-grok-build-plugin --skill repo-scope
Clone the repo
git clone --depth 1 https://github.com/xzawed/claude-grok-build-plugin

Made for: Claude Code.

Or install grok, the plugin that ships this one along with the rest of its 4 skills, 27 commands, 1 agent, 1 hook, 1 MCP server.

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 repo-scope

README.md
[![agentmods](https://agentmods.dev/badge/skills/xzawed/claude-grok-build-plugin/repo-scope/github.svg)](https://agentmods.dev/skills/xzawed/claude-grok-build-plugin/repo-scope)
Your own site
<a href="https://agentmods.dev/skills/xzawed/claude-grok-build-plugin/repo-scope"><img src="https://agentmods.dev/badge/skills/xzawed/claude-grok-build-plugin/repo-scope/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.

agentmods 80×15 button for repo-scope

Your own site · 80×15
<a href="https://agentmods.dev/skills/xzawed/claude-grok-build-plugin/repo-scope"><img src="https://agentmods.dev/badge/skills/xzawed/claude-grok-build-plugin/repo-scope.svg" alt="Reviewed on agentmods" width="80" 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 755 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00755
Opus 5 $0.00000 $0.00378
Sonnet 5 $0.00000 $0.00151
Haiku 4.5 $0.00000 $0.00076

Measured 3d ago against content hash 82fd2f69f2f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

repo-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 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.

.claude/skills/repo-scope/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repo scope gate (claude-grok-build-plugin)

This repo's product scope is closed. docs/09-scope-and-residuals.md is the SSOT.

The rule

The default answer to "what's next?" is: nothingunless docs/10-service-audit-queue.md has open items, in which case the answer is "the top of that queue", and you say so plainly.

Do not open a PR the owner did not ask for. Unrequested "polish" is the failure this repo has already suffered repeatedly — a session looking for work invents it.

The queue is the exception, and only the queue. Its items were found by executing the shipped bundle and re-measuring each result independently (2026-09-05), so they are observed breakage, not invented work. Anything not in that queue still needs an owner goal first. Still ask before opening a PR — having a queue is not standing authorization to work through it.

Before answering "what's next"

  1. Read the 현재 상태 block in root CLAUDE.md, then docs/10-service-audit-queue.md (open defects), then docs/09-scope-and-residuals.md (scope).
  2. Classify every residual before mentioning it. Never present an unclassified list:
Class Meaning May you open a PR?
A — external Consumer / orchestrator repo work No. Doc pointer only
B — manual Human + Claude Code GUI acceptance (docs/09 §5) No. It is a release ritual
C — deferred ACP, pending a stated re-check trigger No. Deferred ≠ next
D — excluded Auto-commit, per-call authMode override No. Out of scope by design
E — new feature Only once the owner states a goal Yes — after done criteria are written
F — measured defect In docs/10-service-audit-queue.md — found by executing the shipped bundle Yes — after the owner picks it up. Not invented work
  1. With no owner goal: if docs/10-service-audit-queue.md has open items, the answer names the top one and stops there — docs/10 A<n> — 열린 결함 <count>건, 착수는 오너 승인 후. Only when that queue is empty is the answer 이 레포 범위 완료 — 외부/수동/보류는 docs/09.

Read the full file on GitHub · 54 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. 3d ago Changed · +10 lines 82fd2f69f2f9
  2. 10d ago First seen · 44 lines · 0 tokens per session scan A c8e9061d86bc

Subscribe to this mod's changes

repo-scope is a skill published in the GitHub repository xzawed/claude-grok-build-plugin (1 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 755 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 2026-08-31.