Is the Scope Check skill free?

Yes. The skill itself is free from dvdarkin/claude-skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Scope Check SkillProof Score?

7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 3/5.

How do I install Scope Check?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Scope Check with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Scope Check

Estimates whether a spec will blow the context budget and proposes chunk boundaries before you write it.

by dvdarkin · dvdarkin/claude-skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 7.6/10
Tested: Jul 16, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · f2ad0ae

Ran its own formulas on a real 3.5KB API design spec (872 prose tokens -> ~40.6K conservative estimate, comfortably GREEN either way) — the math is transparent and reproducible, but MULTIPLIERS.md ships a second, contradictory context-budget threshold table (100K/130K/160K vs. the canonical 50K/75K/100K in CONTEXT-BUDGET.md and SKILL.md) that undercuts its 'grounded, not guesses' claim.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 6/10
Docs & honesty 3/5

What Scope Check does

Gate skill that self-activates before design/plan documents are written, estimating output-token expansion from spec size (language + TDD-level multipliers) and returning a GREEN/YELLOW/ORANGE/RED verdict against a configurable context-window budget. On ORANGE/RED it proposes semantic chunk boundaries and an execution plan; blocks single-file writes that would exceed the 25K-token Read-tool limit.

How to install Scope Check

git clone https://github.com/dvdarkin/claude-skills.git
mkdir -p ~/.claude/skills
cp -r claude-skills/skills/scope-check ~/.claude/skills/scope-check

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Scope Check

/scope-check Estimates whether a spec will blow the context budget and proposes chunk boundaries before you write it.

It also activates on plain-language prompts like these:

Will this API design spec blow our context budget if I write it?
Should I chunk this design doc or write it as a single file?
Estimate how many tokens this spec will expand to before I draft it

Frequently asked questions

Is the Scope Check skill free?: Yes. The skill itself is free from dvdarkin/claude-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Scope Check work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. Ran its own formulas on a real 3.5KB API design spec (872 prose tokens -> ~40.6K conservative estimate, comfortably GREEN either way) — the math is transparent and reproducible, but MULTIPLIERS.md ships a second, contradictory context-budget threshold table (100K/130K/160K vs. the canonical 50K/75K/100K in CONTEXT-BUDGET.md and SKILL.md) that undercuts its 'grounded, not guesses' claim.
What is the Scope Check SkillProof Score?: 7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 3/5.
How do I install Scope Check?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Scope Check with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.