Select the best of independent agent answers with one strong judge. Use when the user requests agent-arena judge mode or invokes /agent-arena-mode:judge.
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
# Agent Arena: judge
Run the **judge** mode. Request: `$ARGUMENTS`.
Plugin root: `${CLAUDE_PLUGIN_ROOT}`.
Persistent data root: `${CLAUDE_PLUGIN_DATA}`.
The Bash tool does NOT receive `CLAUDE_PLUGIN_ROOT`/`CLAUDE_PLUGIN_DATA` as environment variables.
Always use the substituted absolute paths above in commands. Unless `--database` or `--no-library` is given,
pass `--database "${CLAUDE_PLUGIN_DATA}/library.sqlite3"` to `init`. The bundled judge subagent is
`agent-arena-mode:agent-arena-judge` (default claude-opus-5-5/high in frontmatter; pass the assigned judge model and effort per call).
Read [shared orchestration](../../references/orchestration.md),
[runtime adapter](../../references/runtime.md),
[evaluation](../../references/evaluation.md), and
[agent library](../../references/library.md).
Read only the **judge** section in [mode procedures](../../references/modes.md).
Use [role prompts](../../references/prompts.md) and [helper commands](../../references/helper.md) as needed.
Apply the shared protocol with mode fixed to `judge`. The helper's `init` must
receive `--mode judge`. If a conflicting `--mode` argument is supplied, explain
…
The line at the top of this page pins the label git:20261011.397dbb2, 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.
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 (2261 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
ahmadhammoud56/moaa · 5 stars · license MIT · pushed 2026-10-31 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_i3nlfwwa4qdkhbgc
GET https://markdownregistry.com/api/v1/resolve?ref=ahmadhammoud56/moaa/judge
GET https://markdownregistry.com/api/v1/blob/e68b8f9efdd8e0476efd58ffd827e45edcc4dab9c6dd99cc31f8bfa058a037a9
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.
ahmadhammoud56/moaa · plugins/agent-arena-mode/skills/cascade/SKILL.md · Explore many agent proposals and progressively invest in the strongest survivors. Use when the user requests…
ahmadhammoud56/moaa · plugins/agent-arena-mode/skills/effort-trial/SKILL.md · Measure whether council roles find more at a higher effort than at a lower one, per unit of cost, and suggest each…
ahmadhammoud56/moaa · plugins/agent-arena-mode/skills/evolution/SKILL.md · Evolve agent populations through inheritance, selection, mutation, and final synthesis. Use when the user requests…
ahmadhammoud56/moaa · plugins/agent-arena-mode/skills/fold-trial/SKILL.md · Measure whether a council of subagents beats one agent loop on your own tasks, per unit of cost - the same frozen tasks…
ahmadhammoud56/moaa · plugins/agent-arena-mode/skills/karpathy-loop/SKILL.md · Improve something against a fixed number - edit, measure with a script the agent may not change, keep the change if the…
ahmadhammoud56/moaa · plugins/agent-arena-mode/skills/league/SKILL.md · Compare frozen agent answers across repeated Elo-rated matches. Use when the user requests agent-arena league mode or…
ahmadhammoud56/moaa · plugins/agent-arena-mode/skills/library/SKILL.md · Find, inspect, load, and reuse the best saved agent-arena profiles and results from the persistent database. Use when…
ahmadhammoud56/moaa · plugins/agent-arena-mode/skills/redteam/SKILL.md · Use adversarial agents to test, repair, and validate competing solutions. Use when the user requests agent-arena…
ahmadhammoud56/moaa · plugins/agent-arena-mode/skills/swarm/SKILL.md · Run collaborative agent competition with shared findings and iterative elimination. Use when the user requests…
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…
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…
ilang-ai/autocode · skills/judge/SKILL.md · The judgment layer: when AutoCode acts on its own and when it stops and asks, and how it speaks about decisions and…
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.
jeffallan/writing-with-agents · plugin/skills/judge/SKILL.md · Use when editing a draft, checking for AI voice patterns, reviewing prose quality, running readability analysis…
