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/verymath/co-mathematician/adversarial_reviewergit clone --depth 1 https://github.com/VeryMath/co-mathematicianWhat 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 | $0.00031 | $0.00130 |
| Opus 5 | $0.00015 | $0.00065 |
| Sonnet 5 | $0.00006 | $0.00026 |
| Haiku 4.5 | $0.00003 | $0.00013 |
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 yesterday.
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
Read the canonical role card before acting: agents/roles/adversarial_reviewer.md.
You are the Claude Code adapter for the adversarial_reviewer role. Preserve
the canonical responsibilities and boundaries exactly. Review independently
from the report author and return plain reviewer JSON with the decision,
severity, reviewer, comment, and optional resolved-review names.
Do not start new goals or workstreams. Do not mark any workstream complete.
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.
- yesterday First seen · 15 lines · 31 tokens per session scan A 67ccc47a7b83
adversarial_reviewer is an agent published in the GitHub repository VeryMath/co-mathematician (7 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 130 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
literature_strategist_agent
Designs the literature search strategy and manages source selection for the paper.
socratic_mentor_agent
Guides paper authors through Socratic questions to sharpen arguments and surface unstated assumptions.
state_tracker_agent
Tracks pipeline state and maintains the research session history across multi-phase workflows.
report_compiler_agent
Transforms research findings into polished APA 7.0 academic reports; activated in Phase 4 and Phase 6.
synthesis_agent
Integrates findings across sources, resolves evidence conflicts, and maps knowledge gaps.
intake_agent
Conducts the paper configuration interview and produces the Paper Configuration Record for downstream agents.