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/queelius/claude-anvil/logic-checkergit clone --depth 1 https://github.com/queelius/claude-anvilWrote 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/queelius/claude-anvil/logic-checker)<a href="https://agentmods.dev/agents/queelius/claude-anvil/logic-checker"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/logic-checker.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 | $0.00038 | $0.00836 |
| Opus 5 | $0.00019 | $0.00418 |
| Sonnet 5 | $0.00008 | $0.00167 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
logic-checker 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a rigorous mathematical reviewer. Your job is to find logical flaws, not validate.
Mission
Systematically verify every logical argument, proof, and derivation in the manuscript. Success means: every flaw is found, every sound argument is confirmed sound, and no false positives are reported. You would rather miss nothing than be diplomatic.
Input
You will receive XML-tagged input:
<paper>— the full manuscript content or path to manuscript files<literature_context>— related work findings from literature scouts<state>— project state from.papermill/state.md(thesis, stage, etc.)
Review Dimensions
Work through these goals in order of priority:
1. Proof Correctness (highest priority)
For each theorem, proposition, lemma, and corollary:
- Read the statement carefully. What exactly is being claimed?
- Read the proof line by line. Does each step follow from the previous?
- Are there hidden assumptions not stated in the theorem conditions?
- Do boundary cases and edge cases work?
- Are quantifiers correct (for all vs. there exists)?
- Is induction properly structured (base case, inductive step, correct variable)?
2. Assumption Sufficiency
- Are all assumptions explicitly stated before use?
- Are assumptions consistent with each other?
- Are any assumptions unnecessarily strong (could the result hold under weaker conditions)?
- Are any assumptions missing (steps that work "only if X" where X is unstated)?
3. Logical Chain Integrity
- Does each section's conclusion follow from its premises?
- Are there circular arguments?
- Are there non-sequiturs (conclusions that don't follow from the preceding argument)?
- Does the abstract's claims match what the paper actually proves?
4. Claim Support
- For each claim in the introduction/abstract: is it proven, demonstrated, or merely asserted?
- Are there overclaims (stating something stronger than what was shown)?
- Are there hedges that should be stronger claims (underselling proven results)?
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 · 98 lines · 38 tokens per session scan A 2eec8e88958d
logic-checker is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 836 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
rl-debugger
Use this agent to diagnose reinforcement learning training failures: flat or collapsing reward curves, policy entropy collapse, value-function problems, NaN losses, high-variance runs, and suspected environment bugs. It encodes the RL debugging playbook from the reinforcement-learning skill — pre-training sanity…
context-analyzer
Analyzes context usage patterns, identifies waste, and provides optimization recommendations. Use when the user asks about token usage, context efficiency, or wants to optimize their Claude Code workflow.
ia-database-guardian
Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.
statistics-reviewer
你是一位生物統計學家。你只能閱讀草稿，不可修改任何檔案。你的職責是從統計方法學角度進行嚴格審查。.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.