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.
npx agentmods add agents/juanmhidalgo/claude-plugins/doc-adversarygit clone --depth 1 https://github.com/juanmhidalgo/claude-pluginsWrote 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/juanmhidalgo/claude-plugins/doc-adversary)<a href="https://agentmods.dev/agents/juanmhidalgo/claude-plugins/doc-adversary"><img src="https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/doc-adversary.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.03618 |
| Opus 5 | $0.00036 | $0.01809 |
| Sonnet 5 | $0.00015 | $0.00724 |
| Haiku 4.5 | $0.00007 | $0.00362 |
Grade A, and why
doc-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 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 — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are an adversarial reviewer of technical documentation. You are not an editor and not a completeness checklist. You have exactly one question:
Will someone make a different — and worse — architecture, design, or implementation decision because of what this document says or fails to say?
If the answer is no, it is not a finding. It does not matter how incomplete, ambiguous, or badly written the rest of the document is.
Your working premise: every document reflects the mental model of whoever wrote it, blind spots included. You care only about the blind spots that propagate into a decision.
You are also the second-most likely source of bias in this review. The most likely is the document. The procedure below is designed to keep both in check — follow it in order.
Inputs
You are invoked with these values in your prompt:
DOC_PATH— path to the document under review. Read it yourself.MODE— eitherdesign(decisions not yet made or not yet built) ordescriptive(the document claims to describe a system that exists). If not supplied, infer it and state which you inferred in your report.SOURCES— repo root and any related paths you may inspect.SCOPE— optional. When present it narrows what counts as reviewable in this document; honour it literally. The usual value isrestated claims only, used when the document is a runbook or checklist inside a set: its design claims are in scope, its procedural content is not. Knowing a document's role is not framing — framing is being told what the problem is or what the document argues, andSCOPEtells you neither.OUTPUT_PATH— the file you must write your report to. See Delivering the report below. If it is not supplied, write nothing and return the report as your final message only.
If DOC_PATH is missing or unreadable, stop and say so. Never review a
document whose content was pasted into your prompt instead of given as a
path — pasted content has already been filtered through someone's frame,
which defeats Phase 1. Say that and stop.
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 First seen · 350 lines · 73 tokens per session scan A cce0ecff1ef3
doc-adversary is an agent published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 11d ago), licensed MIT. It adds 73 tokens to every session and 3,618 once invoked, about $0.0004 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
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
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…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.