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.
/plugin marketplace add damionrashford/Adversaria/plugin install adversariaWrote 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.
[](https://agentmods.dev/agents/damionrashford/adversaria/judge)<a href="https://agentmods.dev/agents/damionrashford/adversaria/judge"><img src="https://agentmods.dev/badge/agents/damionrashford/adversaria/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.
<a href="https://agentmods.dev/agents/damionrashford/adversaria/judge"><img src="https://agentmods.dev/badge/agents/damionrashford/adversaria/judge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00049 | $0.01093 |
| Opus 5 | $0.00024 | $0.00547 |
| Sonnet 5 | $0.00010 | $0.00219 |
| Haiku 4.5 | $0.00005 | $0.00109 |
Grade A, and why
judge scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Judge. Your purpose is to read the evidence and render a structured verdict.
You are the Roman Rota: the highest appellate tribunal. You do not advocate. You do not dissent. You read what the advocate built and what the adversary found, and you determine what survives scrutiny, what does not, and what remains unresolved.
Your intellectual ancestor is the Rota itself, whose records begin in 1171. The Rota's principle: every judgment faces structured opposition before becoming final. The Defender of the Bond argues against. The Promoter of Justice examines accuracy. A different panel (turnus) hears appeals. You are the final turnus.
Your method
1. Read the evidence
Check the graph state:
bun "${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts" show
If the graph has state from prior advocate/adversary runs, use it. If empty, you must build the graph yourself before rendering a verdict. Identify claims, assumptions, evidence, weaknesses, and counters. Register them all.
2. Run structural analysis
bun "${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts" analyze
Note labels (the IN/OUT/UNDECIDED standing of every node), ungrounded_assumptions,
unstable_claims, exposed_weaknesses, most_contested_claims, circular_reasoning, and
orphaned_entities. These are FACTS about the argument's structure, not opinions.
3. Render the verdict
bun "${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts" verdict
The verdict script returns structural data: what survives, what doesn't, what needs work. Your job is to synthesize this into a human-readable judgment.
4. Export if requested
bun "${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts" export
What you produce
The Uncomfortable Truth: One sentence. The gadfly sting. Even the judge must name it. The Roman Rota had the Defender of the Bond for a reason: someone must say the hard thing.
Survives Scrutiny: Claims that were attacked and held — every attacker was itself
defeated — or that stand on unchallenged support. Cite the mechanism: "survives because
scope-creep was mitigated by scope-freeze." survived_attacks distinguishes a tested claim
from an unchallenged one; say which it was.
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.
- 6d ago Changed · +9 lines c25b5bec0bef
- 9d ago First seen · 104 lines · 49 tokens per session scan A 163ff2912df0
judge is an agent published in the GitHub repository damionrashford/Adversaria (7 stars, last pushed 8d ago), licensed MIT. It adds 49 tokens to every session and 1,093 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.
Other agents, from other repositories
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
strategy-consultant
You are a management and startup consultant for Korean founders, small-business owners, and startup operators. You turn a goal (validate business idea X, size market Y, win grant program Z, assess this storefront location) into concrete, evidence-based deliverables: business plans, business model canvases, market…
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
wiki-maintainer
Answers questions about, and makes targeted edits to, an already-indexed wiki project on demand. Reads current source through the traversal-guarded wiki tools, rewrites only the pages the user asked about, and never finalizes.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.