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/logic_reviewergit clone --depth 1 https://github.com/VeryMath/co-mathematicianWrote 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/verymath/co-mathematician/logic_reviewer)<a href="https://agentmods.dev/agents/verymath/co-mathematician/logic_reviewer"><img src="https://agentmods.dev/badge/agents/verymath/co-mathematician/logic_reviewer.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 | $0.00028 | $0.00116 |
| Opus 5 | $0.00014 | $0.00058 |
| Sonnet 5 | $0.00006 | $0.00023 |
| Haiku 4.5 | $0.00003 | $0.00012 |
Grade A, and why
logic_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 4d 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
Read the canonical role card before acting: agents/roles/logic_reviewer.md.
You are the Claude Code adapter for the logic_reviewer role. Preserve the
canonical responsibilities and boundaries exactly. Review independently from the
report author and return the plain reviewer JSON described by the role card.
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.
- 4d ago First seen · 14 lines · 28 tokens per session scan A 88474f1bc5bd
logic_reviewer is an agent published in the GitHub repository VeryMath/co-mathematician (7 stars, last pushed 5d ago), licensed MIT. It adds 28 tokens to every session and 116 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 2026-08-31.
Other agents, from other repositories
math-critic.en
You are a mathematical assistant with both critical review and implementation capabilities. Your primary task is to evaluate the reliability and applicability of arguments, proposals, or conclusions from a mathematical perspective, while also providing concrete implementation strategies, problem-solving approaches, or…
math-critic
你是一个兼具审查与实现能力的数学助手。主要任务是从数学角度评估论点、方案或结论的可靠性与适用性，同时在必要时提供具体的实现思路、解题方案或证明步骤。你兼任验收把关人：先保证数学正确；仅当产出涉及算法/算子/训练/推理实现时，再按相关维度检查 GPU/工程可行性。纯概念查询与纯密码安全审查不以 GPU 清单作验收门。.
data-cruncher
Run heavy quantitative analysis in isolation — fit many model variants, run cross-validation, simulate power, perform sensitivity analyses, profile slow scripts. Use when the parent conversation needs numerical results but should not be polluted with raw output, large dataframes, or long-running compute. Returns a…
manuscript-drafter
Draft long-form manuscript prose in isolation — full sections (intro / methods / results / discussion / abstract) or full first drafts. Use when the parent conversation needs a polished draft but should not be flooded with thousands of words of prose. Returns a structured digest plus the draft as files.
CodeScientist
CodeScientist, built by [[org:allenai]], is an end-to-end system designed to facilitate [[domain:scientificdiscovery]] through semi-automated experimentation. Utilizing a multiagent architecture, the system generates novel research ideas by applying genetic mutations to combinations of scientific literature and code.…
Agent Hospital
Agent Hospital is a multi-agent, self-evolving system built by [[org:wisdom-pan]] that simulates a complete clinical environment. By utilizing LLMs as autonomous agents, the system models the interactions between patients, nurses, and doctors to facilitate the treatment process. The platform exposes both a cli and a…