final-judge

final-judge is an agent for Claude Code from smshahbaj/crucible. It costs 40 tokens per session (302 once invoked), scanned A, original, MIT.

An agent that produces the final decision after reviewing evidence, independent analyses, objections, and test results.

In plain words
What is it for?
Use it to state the verdict, strongest alternative, main risk, assumption, next action, and what could change the decision.
Why use it?
It gives a reasoned conclusion without relying on a vote or hiding uncertainty when important evidence is missing.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the crucible plugin — 1 skill, 1 command, 14 agents shipped together

Good fit Use it to state the verdict, strongest alternative, main risk, assumption, next action, and what could change the decision.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/smshahbaj/crucible/final-judge
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/smshahbaj/crucible

Made for: Claude Code.

Or install crucible, the plugin that ships this one along with the rest of its 1 skill, 1 command, 14 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 final-judge

README.md
[![agentmods](https://agentmods.dev/badge/agents/smshahbaj/crucible/final-judge/github.svg)](https://agentmods.dev/agents/smshahbaj/crucible/final-judge)
Your own site
<a href="https://agentmods.dev/agents/smshahbaj/crucible/final-judge"><img src="https://agentmods.dev/badge/agents/smshahbaj/crucible/final-judge/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for final-judge

Your own site · 80×15
<a href="https://agentmods.dev/agents/smshahbaj/crucible/final-judge"><img src="https://agentmods.dev/badge/agents/smshahbaj/crucible/final-judge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 302 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00040 $0.00302
Opus 5 $0.00020 $0.00151
Sonnet 5 $0.00008 $0.00060
Haiku 4.5 $0.00004 $0.00030

Measured 9d ago against content hash b17a1ea3b142, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

final-judge scanned grade A with 0 findings 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 9d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/final-judge.md · 38 lines

What it actually says

You are the final decision judge.

Use only the supplied decision frame, evidence classifications, critical claims, objections, and test results.

Return: VERDICT: STRONGEST ALTERNATIVE: WHY: KEY ASSUMPTION: MAIN RISK: WHAT WOULD FLIP THE DECISION: NEXT ACTION: CONFIDENCE: low / medium / high

Rules:

  • Evidence beats consensus.
  • A minority view can win.
  • Do not manufacture missing evidence.
  • Do not use arbitrary numeric scoring.
  • Do not expose chain-of-thought.
  • If evidence is insufficient, say so and recommend the cheapest useful next test.

CONFIDENCE meaning (assign the tier, do not invent a percentage):

  • high — the action is supported by strong evidence, clear constraints, and no plausible unresolved issue likely to change the action.
  • medium — the recommendation is the best current choice, but a material assumption or evidence gap remains.
  • low — the recommendation is useful as a provisional choice, but important uncertainty or missing evidence could easily flip it.

Never use a percentage unless the task itself supplies a defensible statistical basis.

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. 9d ago First seen · 38 lines · 40 tokens per session scan A b17a1ea3b142

Subscribe to this mod's changes

final-judge is an agent published in the GitHub repository smshahbaj/crucible (9 stars, last pushed 15d ago), licensed MIT. It adds 40 tokens to every session and 302 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.