judge

judge is a skill for Claude Code from Borda/AI-Rig. It costs 48 tokens per session (7,822 once invoked), scanned C, original, Apache-2.0.

A research-supervisor review of an experimental plan before it runs. It checks whether the hypothesis, measurements, controls, scope, and strategy form a sound methodology.

In plain words
What is it for?
It is for reviewing a research program’s methodology before running experiments. It does not run experiments, search the literature, or perform general code review.
Why use it?
It can catch weak or unclear experiments before they consume time and computing resources. The result says whether the plan is approved, needs revision, or is blocked.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the research plugin — 8 skills, 2 agents shipped together

Good fit It is for reviewing a research program’s methodology before running experiments. It does not run experiments, search the literature, or perform general code review.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Borda/AI-Rig
Claude Code
/plugin install research

Made for: Claude Code.

Or install research, the plugin that ships this one along with the rest of its 8 skills, 2 agents.

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 judge

README.md
[![agentmods](https://agentmods.dev/badge/skills/borda/ai-rig/judge.svg)](https://agentmods.dev/skills/borda/ai-rig/judge)
Your own site
<a href="https://agentmods.dev/skills/borda/ai-rig/judge"><img src="https://agentmods.dev/badge/skills/borda/ai-rig/judge.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,822 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00048 $0.07822
Opus 5 $0.00024 $0.03911
Sonnet 5 $0.00010 $0.01564
Haiku 4.5 $0.00005 $0.00782

Measured 2d ago against content hash f3ed32696d92, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

judge scanned grade C with 1 finding 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 2d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Judge run dirs don't write `result.jsonl` — exempt from automated 30-day TTL cleanup (per `.claude/rules/foundry-artifact-lifecycle.md` TTL policy — no `result.jsonl` = cleanup skipped); remove manually (`rm -rf .exper
plugins/cc_research/skills/judge/SKILL.md · 464 lines

How it starts

The opening of the file, as written. The whole thing — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research-supervisor review of program.md — validates experimental methodology, emits APPROVED / NEEDS-REVISION / BLOCKED verdict before expensive run loop. Read-only; never modifies code or state.

NOT for: running experiments (use /research:run); designing hypotheses (use research:scientist agent); config quality (/foundry:audit (requires foundry plugin)).

  • Key boundary: end of J3 — methodology and scientific review agents complete, output files written; before J4 validation and J6 verdict.
  • Preserve: RUN_DIR (TMPDIR key), PROGRAM_PATH (TMPDIR key), methodology.md path, scientific-review.md path, SKIP_VALIDATION flag, BRANCH.
  • Clear at J1 start (stale prior run) and at end of J6 after terminal summary printed.

Agent Resolution

Agent resolution: load and follow the protocol below. Contains foundry check + fallback table. If foundry not installed: use table to substitute each foundry:X with general-purpose. Agents: foundry:solution-architect, research:scientist.

# loads: compaction-contract.md
export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}"
_RESEARCH_SHARED=$(python "${CLAUDE_PLUGIN_ROOT:-plugins/cc_research}/bin/resolve_shared.py" 2>/dev/null)  # timeout: 5000
[ -z "$_RESEARCH_SHARED" ] && { echo "! Plugin path resolution failed — ensure research plugin installed and CLAUDE_PLUGIN_ROOT set, or invoke from project root."; exit 1; }
echo "$_RESEARCH_SHARED" > "${TMPDIR:-/tmp}/research-shared-${CSID}"  # cold resolve — every later site reads this sentinel instead of re-running python
cat "$_RESEARCH_SHARED/agent-resolution.md"
Agent Fallback if absent
foundry:solution-architect general-purpose (methodology review quality reduced — ⚠ general-purpose agent may not emit methodology_rating in required format; verdict defaults to NEEDS-REVISION)
research:scientist general-purpose (scientific rigor review quality reduced — ⚠ general-purpose agent may not emit scientific_rating; verdict defaults to NEEDS-REVISION)

Read the full file on GitHub · 464 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. 2d ago Changed · +2 lines f3ed32696d92
  2. 8d ago First seen · 462 lines · 48 tokens per session scan C 8c6ed052c823

Subscribe to this mod's changes

judge is a skill published in the GitHub repository Borda/AI-Rig (26 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 7,822 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.