New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Judge When To Ask

by ilang-ai in ilang-ai/autocode

Decide when AutoCode acts on its own and when it must stop and ask the user.

MITAuto-check passed

Install Judge When To Ask

skills CLI
$ npx skills add ilang-ai/autocode --skill judge-when-to-ask -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ilang-ai/autocode judge-when-to-ask --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ilang-ai/autocode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/judge-when-to-ask .claude/skills/judge-when-to-ask && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
judge-when-to-ask
GitHub stars
103
Token cost
~1.1k tokens
SKILL.md length
457 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Decide when AutoCode acts on its own and when it must stop and ask the user.

  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Judge When To Ask is an agent skill from ilang-ai/autocode. Decide when AutoCode acts on its own and when it must stop and ask the user. Runs before any consequential action — deleting files, spending money, buying a server, deploying to production, force-pushing, binding a domain, sending or publishing anything. Ordinary reversible work proceeds silently; only costly or hard-to-undo actions pause for the user. Powered by I-Lang v5.0 vector judgment.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: You say it. AutoCode ships it. 48 skills. Code to deployment in one session. iLang v5.0 judgment + secret-safe deploys. Free forever. The licence is MIT.

Example prompts

  • “/judge-when-to-ask”

What it can do on your machine

Read from SKILL.md and the folder at commit 8629dc2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Judge When To Ask loads about 1.1k tokens when it runs. Until then it costs about 103 tokens; SKILL.md has 457 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~103
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ilang-ai/autocode at commit 8629dc2, republished under its MIT licence (© ilang-ai). 457 words, ~1,081 tokens.

Download SKILL.mdSave it as .claude/skills/judge-when-to-ask/SKILL.md (or your agent's skills folder).
name
judge-when-to-ask
description
Decide when AutoCode acts on its own and when it must stop and ask the user. Runs before any consequential action — deleting files, spending money, buying a server, deploying to production, force-pushing, binding a domain, sending or publishing anything. Ordinary reversible work proceeds silently; only costly or hard-to-undo actions pause for the user. Powered by I-Lang v5.0 vector judgment.
version
5.0.0

::PRIOR{completion:assume_incomplete|authority:developer} ::PRIOR{execution:act_when_safe|authority:developer}

::GENE{judge-when-to-ask|conf:confirmed|scope:global} T:default_act_on_reversible_low_cost_work T:stop_and_ask_before_costly_or_irreversible T:one_question_when_asking|yes_no_or_plain T:never_expose_internal_judgment_terms A:ask_about_reversible_trivia⇒decide_self A:act_silently_on_irreversible_or_paid⇒stop_first A:show_user_vector_or_mode_words⇒plain_language_only

AutoCode's promise is "AI decides everything, you just say yes or no." That only

works if AI decides the RIGHT things on its own and asks about the RIGHT things.

This skill draws that line using I-Lang v5.0 judgment. The user never sees any of

the machinery below — they only experience an AI that handles the small stuff and

checks in on the big stuff.

::JUDGE{protocol:ilang-v5.0}

Weigh the pending action across the v5.0 dimensions (higher = safer to act alone):

consequence (how bad if wrong), reversibility (how easily undone),

sovereignty (does it spend the user's money without their consent), authority (is it the user's to authorize),

certainty (do I actually know what they want), capability (can I reliably do it).

First match wins — conservative cascade. Modes are internal; never spoken.

RULE:action_hits_a_hard_stop # deletes user data with no backup, force-pushes shared history, publishes # something public irreversibly, or the user earlier said "never do X" => MODE:STOP => to_user(plain): state the risk in one sentence, ask if they really want it

RULE:i_dont_actually_know_what_they_want # the request is ambiguous in a way where guessing wrong is expensive => MODE:ASK => to_user(plain): ONE yes/no or plain question, then wait

RULE:it_costs_money_or_buys_a_service # buying a VPS, registering a domain, anything that charges the user => MODE:CONFIRM => to_user(plain): "This costs about $X. Go ahead?" — name the price, wait

RULE:it_touches_production_or_is_hard_to_undo # deploying to a live site, DB migration, DNS change => MODE:CONFIRM => to_user(plain): "I'll do X, ok?" — one line, wait for yes

RULE:reversible_and_within_capability # writing code, scaffolding, local edits, running a build, a revertable commit => MODE:EXEC_AUTO => proceed silently, report after ("✅ done")

DEFAULT => MODE:CONFIRM # when unsure, ask rather than surprise the user

::ACTIVATE{judge-when-to-ask} ON:before_delete ON:before_deploy ON:before_purchase ON:before_domain_bind ON:before_force_push ON:before_publish ON:ambiguous_request OFF:reversible_local_edit(no cost, no external effect)

Show full SKILL.md (174 more words)Show less

The judgment is RELATIVE by design. "Deploy to production" for a throwaway demo

leans EXEC_AUTO; the same deploy on a project the user called important leans CONFIRM.

Same command, different call — because AutoCode applies the user's own context,

not a fixed rule. That is what makes it feel like it understands them.

::EXAMPLE{

reversible work → just do it, no question

action: create a login page component result: EXEC_AUTO — builds it, then "✅ Login page done (3/8)"

costs money → name the price, wait

action: buy a VPS to deploy result: CONFIRM — "To put this online you'll need a small server, about $6/month. Want me to set that up?"

irreversible + unclear → stop and ask, in plain words

action: user says "clear everything and start over" in a repo with real work result: STOP — "That will erase everything we've built so far and it can't be undone. Are you sure?"

never say this to the user:

forbidden_output: "sovereignty=0.2, resolving to M8 STOP" correct_output: "This can't be undone — sure you want to?" }

Powered by I-Lang v5.0 | ilang.ai | protocol: github.com/ilang-ai/ilang-spec

© ilang-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/judge-when-to-ask of ilang-ai/autocode.

Open the folder on GitHubat commit 8629dc2

Compare with similar skills

Judge When To Ask next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Judge When To Ask compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Judge When To Ask this skillilang-ai/autocode103—~1.1kAutomated safety check: PassMIT
Decidealirezarezvani/claude-skills28k—~871Automated safety check: PassMIT
Decidesuperset-sh/superset15k—~695Automated safety check: PassCustom licence
JudgeNeoLabHQ/context-engineering-kit1.8k—~2kAutomated safety check: PassGPL-3.0
Router Actvercel/next.js143k—~3.1kAutomated safety check: PassMIT
AI Act Readinessalirezarezvani/claude-skills28k—~1.8kAutomated safety check: PassMIT

Similar skills

  • Decide

    alirezarezvani/claude-skills

    /cs:decide <memo — Log a decision to two-layer memory via decision-logger.

    28k GitHub stars~871 tokensUpdated 1 mo ago
    Auto-check passed

  • Decide

    superset-sh/superset

    Walk the user through design or implementation decisions one at a time, or review completed code one change at a time.

    15k GitHub stars~695 tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Judge

    NeoLabHQ/context-engineering-kit

    Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation

    1.8k GitHub stars~2k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Router Act

    vercel/next.js

    Official

    How to write end-to-end tests using createRouterAct and LinkAccordion.

    143k GitHub stars~3.1k tokensUpdated today
    Testing & QAAuto-check passed

  • AI Act Readiness

    alirezarezvani/claude-skills

    /cs:ai-act-readiness <system — EU AI Act 6-question forcing interrogation.

    28k GitHub stars~1.8k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed

  • Do And Judge

    NeoLabHQ/context-engineering-kit

    Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop

    1.8k GitHub stars~14k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

More from ilang-ai/autocode

All 8 skills in this repo

  • Security

    ilang-ai/autocode

    Auto-apply security basics and block deploys that would leak secrets.

    103 GitHub stars~324 tokensUpdated 19 days ago
    Auto-check passed

  • Build Feature

    ilang-ai/autocode

    Build one feature at a time. An agent skill from ilang-ai/autocode.

    103 GitHub stars~177 tokensUpdated 19 days ago
    Auto-check passed

  • Env Setup

    ilang-ai/autocode

    Help complete beginners set up their development environment.

    103 GitHub stars~313 tokensUpdated 19 days ago
    Auto-check passed

  • Ask Smart

    ilang-ai/autocode

    Before coding, determine what to ask. An agent skill from ilang-ai/autocode.

    103 GitHub stars~150 tokensUpdated 19 days ago
    Auto-check passed

  • Auto Quality

    ilang-ai/autocode

    Silent quality check after every feature. An agent skill from ilang-ai/autocode.

    103 GitHub stars~129 tokensUpdated 19 days ago
    Auto-check passed

  • Build Scaffold

    ilang-ai/autocode

    Create project skeleton. An agent skill from ilang-ai/autocode.

    103 GitHub stars~161 tokensUpdated 19 days ago
    Auto-check passed

Questions about Judge When To Ask

What does Judge When To Ask do?

Decide when AutoCode acts on its own and when it must stop and ask the user. Judge When To Ask is an agent skill from ilang-ai/autocode. Decide when AutoCode acts on its own and when it must stop and ask the user.

How do I install Judge When To Ask in Claude Code?

Run `npx skills add ilang-ai/autocode --skill judge-when-to-ask -a claude-code`. Or copy the skill folder (skills/judge-when-to-ask in ilang-ai/autocode) into .claude/skills/judge-when-to-ask in your project. Claude Code loads it when a task matches its description.

How do I install Judge When To Ask in Codex?

Run `npx skills add ilang-ai/autocode --skill judge-when-to-ask -a codex`. Or copy the skill folder (skills/judge-when-to-ask in ilang-ai/autocode) into .agents/skills/judge-when-to-ask in your project. Codex loads it when a task matches its description.

Can I use Judge When To Ask in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ilang-ai/autocode --skill judge-when-to-ask -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/judge-when-to-ask, .gemini/skills/judge-when-to-ask, .github/skills/judge-when-to-ask and .opencode/skills/judge-when-to-ask in your project.

What does Judge When To Ask need to run?

SKILL.md names no scripts, command-line tools or credentials: Judge When To Ask is instructions for the agent only.

Does Judge When To Ask access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Judge When To Ask safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Judge When To Ask use?

Judge When To Ask is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Judge When To Ask use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Judge When To Ask?

Skills that share tags, products or a category with Judge When To Ask: Decide (alirezarezvani/claude-skills, 28k stars), Decide (superset-sh/superset, 15k stars), Judge (NeoLabHQ/context-engineering-kit, 1.8k stars) and Router Act (vercel/next.js, 143k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Judge When To Ask?

ilang-ai (a GitHub organization) maintains it in ilang-ai/autocode, which has 103 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 22, 2026.

Source: ilang-ai/autocode on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.