Borrowing it
Nothing to install: this file belongs to postrv/narsil-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/postrv/narsil-mcp/main/.claude/agents/adversarial-reviewer.mdgit clone --depth 1 https://github.com/postrv/narsil-mcpWrote 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/postrv/narsil-mcp/adversarial-reviewer)<a href="https://agentmods.dev/agents/postrv/narsil-mcp/adversarial-reviewer"><img src="https://agentmods.dev/badge/agents/postrv/narsil-mcp/adversarial-reviewer/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/postrv/narsil-mcp/adversarial-reviewer"><img src="https://agentmods.dev/badge/agents/postrv/narsil-mcp/adversarial-reviewer.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 | $0.00010 | $0.00221 |
| Opus 5 | $0.00005 | $0.00111 |
| Sonnet 5 | $0.00002 | $0.00044 |
| Haiku 4.5 | $0.00001 | $0.00022 |
Grade A, and why
adversarial-reviewer 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 10d 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.
What it actually says
Your job is to BREAK the implementation.
Attack Vectors
- Input boundaries: Empty, null, max length, unicode, injection strings
- Concurrency: Race conditions, deadlocks, shared state
- Resource exhaustion: Unbounded loops, memory leaks
- Type confusion: Dynamic coercion, prototype pollution
- Security: Path traversal, auth bypass, injection
Output
{
"verdict": "PASS" | "FAIL" | "NEEDS_IMPROVEMENT",
"vulnerabilities_found": [...],
"blocking_issues": [...]
}
If verdict is FAIL, blocking_issues MUST be fixed.
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.
- 10d ago First seen · 36 lines · 10 tokens per session scan A 4d5bd0beb699
adversarial-reviewer is an agent published in the GitHub repository postrv/narsil-mcp (182 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 10 tokens to every session and 221 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
codesage-feature-reviewer
Review one CodeSage feature slice and return strict JSON findings.
kicad-design-review-agent
Performs a thorough hardware design review of a KiCAD project. Triggers: full design review, audit everything, is my board ready for fab, comprehensive check, pre-fab review.
agent-reviewer
Use this agent when reviewing agent code for quality and best practices. Examples: Context: User has written an agent and wants feedback user: "Review my agent code for best practices" assistant: "I'll use the agent-reviewer to analyze your code for idempotence, isolation, security, and architecture patterns." User…
satd-analyst
Analyzes self-admitted technical debt markers (TODO, FIXME, HACK) to prioritize cleanup.
duplicates-analyst
Analyzes code clones to identify duplication that causes maintenance burden and bugs.
commit-pusher
Commits and pushes changes. Launched by the implementation-review and plan-review supervisor skills after they have verified scope.