adversary

A code-review subagent that investigates one suspected bug at a time by reading the relevant code and checking it against the matching hazard rules.

In plain words
What is it for?
Use it to verify individual findings, including cases involving discarded fields or downgraded errors, after the initial scan.
Why use it?
It turns a scanner result into an evidence-based decision about whether the suspected issue is a real bug.

Agent

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.

agentmods
npx agentmods add agents/orin-dx/agent-plugins/adversary
Clone the repo
git clone --depth 1 https://github.com/orin-dx/agent-plugins
Per session 261 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,332 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00261 $0.02332
Opus 5 $0.00130 $0.01166
Sonnet 5 $0.00052 $0.00466
Haiku 4.5 $0.00026 $0.00233

Measured 2d ago against content hash c0e1387c0082, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adversary 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 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.

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.

plugins/ranger/agents/adversary.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<load_first> Check the input candidate@1's taxonomy field first, then load only what that one taxonomy needs:

  • taxonomy is T7 or T10: load rust-hazards-t7-t10.md (Rust) or typescript-hazards-t7-t10.md (TypeScript/JavaScript)
  • any other taxonomy: load rust-hazards.md (Rust) or typescript-hazards.md (TypeScript/JavaScript) Language is declared in the recon manifest under the "language" field. Never load both files for one candidate — one candidate has exactly one taxonomy. </load_first>

Read the full file on GitHub · 114 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 First seen · 114 lines · 261 tokens per session scan A c0e1387c0082

Subscribe to this mod's changes

adversary is an agent published in the GitHub repository orin-dx/agent-plugins (1 stars, last pushed 5d ago), licensed MIT. It adds 261 tokens to every session and 2,332 once invoked, about $0.0013 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.