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 instructions/zxyasfas/paper_format_agent/agents-mdgit clone --depth 1 https://github.com/zxyasfas/paper_format_agentWrote 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/instructions/zxyasfas/paper_format_agent/agents-md)<a href="https://agentmods.dev/instructions/zxyasfas/paper_format_agent/agents-md"><img src="https://agentmods.dev/badge/instructions/zxyasfas/paper_format_agent/agents-md.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 | $0.00210 | $0.00210 |
| Opus 5 | $0.00105 | $0.00105 |
| Sonnet 5 | $0.00042 | $0.00042 |
| Haiku 4.5 | $0.00021 | $0.00021 |
Grade A, and why
paper_format_agent AGENTS.md 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
Agent Instructions
This repository contains a local-first academic paper formatting agent. Keep changes narrow, deterministic, and test-backed.
Commands
python tools/validate_skill.py
python -m unittest discover -s tests -p "test_*.py"
python tools/compile_check.py
Guardrails
- Do not commit real papers, private templates, API keys, generated DOCX/PDF files, or local output folders.
- Preserve content by default. Formatting changes must not rewrite academic prose unless a user explicitly opts in.
- Prefer synthetic fixtures and short rule snippets in tests.
- When adding a new format rule, include a test that fails without the change.
High-Value PR Areas
- Template rules for more schools, journals, and conferences.
- DOCX inspection and scoring coverage for tables, figures, equations, references, headers, and footers.
- Better reports that explain what failed and how to fix it.
- Local-only integrations such as MCP, GitHub Actions, and batch processing.
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 · 26 lines · 210 tokens per session scan A dea5ee3ea63d
paper_format_agent AGENTS.md is an instructions file published in the GitHub repository zxyasfas/paper_format_agent (79 stars, last pushed 1mo ago), licensed MIT. It adds 210 tokens to every session, about $0.0011 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 instructions, from other repositories
latex-arxiv-SKILL AGENTS.md
Instructions for appautomaton/latex-arxiv-SKILL, covering agents.md, workflow (issue‑driven) and non‑negotiable rules.
scientific-writing CLAUDE.md
Instructions for koljaschoepe/scientific-writing, covering scientific writing framework, schnellstart, workflow, befehle and regeln für generierte texte.
economics-paper-reviewer CLAUDE.md
Instructions for viplee110/economics-paper-reviewer: This repository is a portable English-only economics paper pre-review skill.
thesis-proposal-skills AGENTS.md
AGENTS.md instructions for hutzelmann/thesis-proposal-skills, covering agents.md, what this repo is, spec-first workflow (mandatory), hard rules and python conventions.
SciCrucible CLAUDE.md
Claude Code instructions for Xinyang-Li666/SciCrucible, covering 科学知识库, 知识库结构, 可用命令, 项目目录 and 工作原则.
thesis-proposal-skills CLAUDE.md
Claude Code instructions for hutzelmann/thesis-proposal-skills, a project described as: Write a convincing thesis proposal with support from AI.