Is the Judge When To Ask skill free?

Yes. The skill itself is free from ilang-ai/autocode. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Judge When To Ask SkillProof Score?

6.8/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 5/10, docs & honesty 3/5.

How do I install Judge When To Ask?

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 Judge When To Ask 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.

Judge When To Ask

Decides when an autonomous coding agent should act silently vs. stop and ask before costly or irreversible actions.

by ilang-ai · ilang-ai/autocode

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 6.8/10
Tested: Jul 17, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 9b27f9a

Fed it a mixed batch (rename a local variable, force-push shared main, buy a $6/mo VPS, wipe-and-reseed a real DB) and it returned ACT / CONFIRM / CONFIRM / STOP with correct plain-language prompts. But a no-skill baseline reached the identical four decisions, so it formalizes judgment rather than improving it, and the 'I-Lang v5.0 vector judgment' branding is prose pseudo-syntax with no real engine behind it.

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

Installs cleanly 5/5
Triggers reliably 4/5
Output vs. baseline 5/10
Docs & honesty 3/5

What Judge When To Ask does

A decision-gate skill for autonomous coding agents: reversible low-cost work proceeds silently, while deletes, force-pushes, deploys, purchases, and domain binds pause for a plain-language yes/no. Triggers before consequential actions and on ambiguous requests.

How to install Judge When To Ask

git clone https://github.com/ilang-ai/autocode.git
mkdir -p ~/.claude/skills
cd autocode && cp -r skills/judge-when-to-ask ~/.claude/skills/judge-when-to-ask

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

Commands — how to trigger Judge When To Ask

/judge-when-to-ask Decides when an autonomous coding agent should act silently vs. stop and ask before costly or irreversible actions.

It also activates on plain-language prompts like these:

Should you check with me before force-pushing to our shared main branch
We're about to wipe and reseed the production database, confirm first
Decide which of these pending changes are safe to run without asking me

Frequently asked questions

Is the Judge When To Ask skill free?: Yes. The skill itself is free from ilang-ai/autocode. SkillProof publishes the install command and an independent test verdict at no cost.
Does Judge When To Ask work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Works with setup. Fed it a mixed batch (rename a local variable, force-push shared main, buy a $6/mo VPS, wipe-and-reseed a real DB) and it returned ACT / CONFIRM / CONFIRM / STOP with correct plain-language prompts. But a no-skill baseline reached the identical four decisions, so it formalizes judgment rather than improving it, and the 'I-Lang v5.0 vector judgment' branding is prose pseudo-syntax with no real engine behind it.
What is the Judge When To Ask SkillProof Score?: 6.8/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 5/10, docs & honesty 3/5.
How do I install Judge When To Ask?: 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 Judge When To Ask 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.