judge SKILL.md skillA

judge from ilang-ai/autocode is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add ilang-ai/autocode/judge@v6.2.2

Pins v6.2.2 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
ilang-ai/autocode
Path
skills/judge/SKILL.md
Versions recorded
3
Latest version
v6.2.2, committed Oct 22, 2026
First version recorded
Oct 15, 2026
Size
4,962 bytes
Repository stars
104
License
MIT

The judgment layer: when AutoCode acts on its own and when it stops and asks, and how it speaks about decisions and money. iLang v5.0: perception sets the 11 dimensions, the frozen reference function f_v5 sets the mode, the user sees one plain line. Runs before every consequential action.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# judge — cross-cutting: when to act, when to ask, how to say it

[PROTOCOL:iLang|v=5.0|layer=declaration]

AutoCode's promise is "AI decides everything, you only say yes or no". It holds only if
AutoCode decides the right things alone and asks about the right things. iLang v5.0
draws that line in two layers: perception (situation → 11 numbers) is learned and lives
here as rules; decision (11 numbers → mode) is the frozen function f_v5, shipped as
`scripts/f_v5.py`. The user never sees any of it: one plain line, as PRODUCT-4 requires.

::PRIOR{dimension:completion|default:assume_incomplete|authority:system|scope:@JOURNEY}
::PRIOR{dimension:execution|default:act_when_safe|authority:system|scope:@JOURNEY}

::GENE{judge|conf:confirmed|scope:global}
  T:default_act_on_reversible_low_cost_work
  T:stop_before_costly_or_irreversible|say_the_risk_or_the_price_in_one_line
  T:questions_are_the_users_not_the_engineers|max=2|yes_no_or_plain|one_message
  T:decide_between_options_yourself|say_why_in_one_sentence
  T:explain_decisions_as_cost_speed_stability|one_sentence|no_jargon_for_beginners
  T:money_in_local_currency|compare_with_real_world|free_first|monthly_and_yearly_total
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ilang-ai/autocode/judge@sha256:139264f5af1f834d

The line at the top of this page pins the label v6.2.2, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_l5blwfll3klgytfg.svg)](https://markdownregistry.com/a/art_l5blwfll3klgytfg)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Oct 15, 2026 and Oct 22, 2026, about one every 4 days.

versioncommittedcommitsizeaudit
v6.2.2 latest2026-10-22 970f6dd 4,962 BA view · diff
v6.2.12026-10-15 18416ad 4,962 BA view · diff
v6.2.02026-10-15 0d09ca3 4,962 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4962 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

ilang-ai/autocode · 104 stars · license MIT · pushed 2026-10-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_l5blwfll3klgytfg
GET https://markdownregistry.com/api/v1/resolve?ref=ilang-ai/autocode/judge
GET https://markdownregistry.com/api/v1/blob/139264f5af1f834d486521422f9ffd4f480e9eb99844478a121e9e9475c2842d

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from ilang-ai/autocode

fix SKILL.md skill
ilang-ai/autocode · skills/fix/SKILL.md · Cross-cutting: when something breaks. Observe, then reason, then the smallest fix, then verify the symptom is gone and…
v6.2.2 · audit A · 104 stars
hand-back SKILL.md skill
ilang-ai/autocode · skills/hand-back/SKILL.md · S7 of see-it-ship-it: what the person hears. Progress lines while building (percentage, fraction, three lines max)…
v6.2.2 · audit A · 104 stars
memory SKILL.md skill
ilang-ai/autocode · skills/memory/SKILL.md · Cross-cutting: what AutoCode remembers and how every session starts. Loads project state and global preferences at the…
v6.2.2 · audit A · 104 stars
plan SKILL.md skill
ilang-ai/autocode · skills/plan/SKILL.md · S3 of see-it-ship-it: cut the work into steps that each end in something the person can click, with minutes not hours…
v6.2.2 · audit A · 104 stars
product-study SKILL.md skill
ilang-ai/autocode · skills/product-study/SKILL.md · Study an existing product from its public pages and turn it into an evidence-backed blueprint plus an MVP cut that…
v6.2.2 · audit B · 104 stars
security SKILL.md skill
ilang-ai/autocode · skills/security/SKILL.md · Auto-apply security basics and block deploys that would leak secrets. Never ask the user about security choices — just…
v6.2.2 · audit A · 104 stars
see SKILL.md skill
ilang-ai/autocode · skills/see/SKILL.md · S1 of see-it-ship-it: understand what the person wants from the way they said it. Classify intent silently, detect…
v6.2.2 · audit A · 104 stars
ship SKILL.md skill
ilang-ai/autocode · skills/ship/SKILL.md · S6 of see-it-ship-it: put it at a public URL. Secret scan first; static builds go to GitHub Pages at no cost (sign-up…
v6.2.2 · audit A · 104 stars
verify SKILL.md skill
ilang-ai/autocode · skills/verify/SKILL.md · S5 of see-it-ship-it: prove it works before saying so. Silent quality checks after every feature, a full review of…
v6.2.2 · audit A · 104 stars

Every file in ilang-ai/autocode

Other files named judge

judge SKILL.md skill
aiskillstore/marketplace · skills/2389-research/judge/SKILL.md · Scoring framework for test-kitchen cookoff and omakase-off. Invoked at Phase 4 to evaluate implementations using…
git:20260113.222b7de · audit A · 439 stars
judge SKILL.md skill
aiskillstore/marketplace · skills/2389-research/test-kitchen/judge/SKILL.md · Scoring framework for test-kitchen cookoff and omakase-off. Invoked at Phase 4 to evaluate implementations using…
git:20260113.222b7de · audit A · 439 stars
judge SKILL.md skill
simota/agent-skills · judge/SKILL.md · Reviewing code via multi-engine orchestration (Claude + Codex) on three axes — secure, correct, and lean — shipping…
git:20261009.1e21383 · audit A · 93 stars
judge SKILL.md skill
saadshahd/moo.md · hope/skills/judge/SKILL.md · One committed verdict on something that exists, cited. Use when something exists and a claim about it needs a verdict.
git:20260927.d54c79c · audit A · 38 stars
judge SKILL.md skill
borda/ai-rig · plugins/cc_research/skills/judge/SKILL.md · Research-supervisor review of program.md — validates experimental methodology (hypothesis clarity, measurement…
git:20261021.076157a · audit A · 28 stars
judge SKILL.md skill
jhostalek/dotclaude · skills/judge/SKILL.md · Obtain an independent review of the approach and trade-offs in completed work.
git:20260905.f4df904 · audit A · 11 stars
judge SKILL.md skill
2389-research/test-kitchen · skills/judge/SKILL.md · Scoring framework for test-kitchen cookoff and omakase-off. Invoked at Phase 4 to evaluate implementations using…
git:20260706.bce1096 · audit A · 4 stars

Browse by kind, by grade A, or by owner.