llm-tech-report-maintenance

llm-tech-report-maintenance is a cursor rule for Cursor from ChenZiHong-Gavin/llm-tech-report. It costs 0 tokens per session (1,077 once invoked), scanned A, original, MIT.

A set of repository rules for maintaining a list of large-language-model technical reports in README.md and its Chinese mirror. The reports are stored as Markdown tables containing dates, model names, types, and links.

In plain words
What is it for?
Use it when adding or updating company report entries, fixing links, checking table structure, or applying the repository's naming, ordering, and commit rules.
Why use it?
It prevents report entries from drifting into inconsistent formats or using the wrong kind of source. It also keeps the process focused on links rather than downloading or reading PDF files.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it when adding or updating company report entries, fixing links, checking table structure, or applying the repository's naming, ordering, and commit rules.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/chenzihong-gavin/llm-tech-report/llm-tech-report-maintenance
Install

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.

Clone the repo
git clone --depth 1 https://github.com/ChenZiHong-Gavin/llm-tech-report

Made for: Cursor.

Wrote 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.

agentmods badge for llm-tech-report-maintenance

README.md
[![agentmods](https://agentmods.dev/badge/rules/chenzihong-gavin/llm-tech-report/llm-tech-report-maintenance/github.svg)](https://agentmods.dev/rules/chenzihong-gavin/llm-tech-report/llm-tech-report-maintenance)
Your own site
<a href="https://agentmods.dev/rules/chenzihong-gavin/llm-tech-report/llm-tech-report-maintenance"><img src="https://agentmods.dev/badge/rules/chenzihong-gavin/llm-tech-report/llm-tech-report-maintenance/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for llm-tech-report-maintenance

Your own site · 80×15
<a href="https://agentmods.dev/rules/chenzihong-gavin/llm-tech-report/llm-tech-report-maintenance"><img src="https://agentmods.dev/badge/rules/chenzihong-gavin/llm-tech-report/llm-tech-report-maintenance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,077 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01077
Opus 5 $0.00000 $0.00539
Sonnet 5 $0.00000 $0.00215
Haiku 4.5 $0.00000 $0.00108

Measured 9d ago against content hash 16472aacdde6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

llm-tech-report-maintenance 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 9d 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.

.cursor/rules/llm-tech-report-maintenance.mdc · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Tech Report Maintenance

README.md (and its mirror README_CN.md) is the only data file — all reports live there as Markdown tables.

Core rule: links only — never download PDFs, never read/parse PDF content.

README schema

Each company is an ## H2 heading containing one Markdown table:

## Company Name

| Date | Model | Type | Link |
|:-----|:------|:-----|:-----|
| YYYY-MM | Model Name | Type | [Display Text](URL) |

Field definitions

Field Format Example
Date YYYY-MM 2025-01
Model Official model name / version DeepSeek-R1
Type One of the values below Paper
Link [Display Text](URL) [Technical Report](https://arxiv.org/abs/…)

Allowed Type values

Type When to use
Paper Peer-reviewed or arXiv publication
Technical Report Official technical document (not peer-reviewed)
System Card Safety / capability evaluation doc (OpenAI, Anthropic style)
Model Card Model spec / limitations doc (Google, HuggingFace style)
Blog Official company blog post (when no paper exists)
GitHub Official repo (when no paper or blog exists)

Link priority (highest → lowest)

  1. arXiv (arxiv.org/abs/…) — most stable
  2. Official CDN (cdn.openai.com, assets.anthropic.com, storage.googleapis.com)
  3. Official blog (openai.com/blog, qwen.ai/blog)
  4. GitHub repo (github.com/org/repo)
  5. Web Archive (web.archive.org) — only when the original is dead

If a model has both a paper and a system card, add two separate rows.

Operations

Add a report to an existing company

  1. Read README.md
  2. Find the company's H2 section
  3. Confirm the model is NOT already listed (avoid duplicates)
  4. Append a new row at the END of that company's table
  5. Keep chronological order (oldest → newest)
  6. Mirror the same edit into README_CN.md, then commit

Read the full file on GitHub · 114 lines

Changes

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.

  1. 9d ago First seen · 114 lines · 0 tokens per session scan A 16472aacdde6

Subscribe to this mod's changes

llm-tech-report-maintenance is a cursor rule published in the GitHub repository ChenZiHong-Gavin/llm-tech-report (37 stars, last pushed 21d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,077 tokens. 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.