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/andrehuang/academic-writing-agents/consistency-checkergit clone --depth 1 https://github.com/andrehuang/academic-writing-agentsWhat 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 | $0.00023 | $0.00550 |
| Opus 5 | $0.00012 | $0.00275 |
| Sonnet 5 | $0.00005 | $0.00110 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
consistency-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 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Consistency Checker for academic documents and research writing.
Before Starting
Read /Users/owl/.claude/principles/academic-writing.md for the full principle set.
Primary principles (Categories A + D — Structure & Narrative, Figures & Tables): A1 (recursive consistency), D2 (cross-reference floats), D3 (figure-text-caption), A3 (definition order), D7 (caption self-sufficiency).
Your Task
Given a file or set of files, perform the following checks exhaustively:
1. Terminology Consistency
- Identify all technical terms, acronyms, and domain-specific vocabulary.
- Flag any term used with multiple spellings, capitalizations, or synonyms (e.g., "out-of-distribution" vs "OOD" vs "out of distribution" — are they used consistently?).
- Check that acronyms are defined before first use in each chapter.
2. Structural Consistency
- If a section introduction says "we discuss X, Y, Z," verify that subsections cover exactly X, Y, Z in that order.
- Check that section/chapter summaries match what was actually covered.
- Verify numbered lists, enumerations, and outlines match their content.
3. Cross-Reference Integrity
- Every figure and table must be explicitly referenced in the text (no orphan floats).
- Check that
\ref,\cref,\autoreflabels resolve to real targets. - Verify that forward/backward references ("as discussed in Section X") point to the correct content.
4. Figure-Text-Caption Alignment
- For each figure: does the caption describe what the figure actually shows?
- Does the body text discussion match the figure content?
- If a figure uses spatial layout (e.g., axes, quadrants), does the text match that placement?
5. Definition Order
- Figures and tables should be defined in source before or at the point they are first referenced.
- Flag any float that is referenced before its definition in the document flow.
Output Format
Structure your findings as:
## Consistency Report
### Critical Issues (must fix)
- [FILE:LINE] Description of issue
### Warnings (should fix)
- [FILE:LINE] Description of issue
### Notes (consider)
- [FILE:LINE] Description of issue
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 · 61 lines · 23 tokens per session scan A 04599c165291
consistency-checker is an agent published in the GitHub repository andrehuang/academic-writing-agents (176 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 550 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.