Borrowing it
Nothing to install: this file belongs to ChenZiHong-Gavin/llm-tech-report. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ChenZiHong-Gavin/llm-tech-report/main/AGENTS.mdgit clone --depth 1 https://github.com/ChenZiHong-Gavin/llm-tech-reportWrote 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/chenzihong-gavin/llm-tech-report/agents-md)<a href="https://agentmods.dev/instructions/chenzihong-gavin/llm-tech-report/agents-md"><img src="https://agentmods.dev/badge/instructions/chenzihong-gavin/llm-tech-report/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 5.1 | $0.01353 | $0.01353 |
| Opus 5 | $0.00677 | $0.00677 |
| Sonnet 5 | $0.00271 | $0.00271 |
| Haiku 4.5 | $0.00135 | $0.00135 |
Grade A, and why
llm-tech-report 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 8d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents (Codex, etc.) working in the llm-tech-report repo.
Project
A curated index of LLM technical reports, papers, and model/system cards.
llm-tech-report/
├── README.md ← The only data file. All reports live here.
├── README_CN.md ← Chinese mirror of README.md — keep in sync.
├── CONTRIBUTING.md ← Human-readable contribution guide
├── LICENSE
└── .claude/skills/… ← Detailed skill docs (maintenance + logo-generation)
Core rule: links only — never download PDFs, never read/parse PDF content.
There are two kinds of task: (A) maintaining the report data and (B) regenerating the logo.
A. Report maintenance
README.md holds one Markdown table per company under an ## H2 heading:
## Company Name
| Date | Model | Type | Link |
|:-----|:------|:-----|:-----|
| YYYY-MM | Model Name | Type | [Display Text](URL) |
Field definitions
- Date —
YYYY-MM(e.g.2025-01) - Model — official model name / version (e.g.
DeepSeek-R1) - Type — one of the allowed values below
- Link —
[Display Text](URL)
Allowed Type values
Paper— peer-reviewed or arXiv publicationTechnical 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)
- arXiv (
arxiv.org/abs/…) — most stable - Official CDN (
cdn.openai.com,assets.anthropic.com,storage.googleapis.com) - Official blog (
openai.com/blog,qwen.ai/blog) - GitHub repo (
github.com/org/repo) - 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
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.
- 8d ago First seen · 137 lines · 1,353 tokens per session scan A 326f8c64fcfc
llm-tech-report AGENTS.md is an instructions file published in the GitHub repository ChenZiHong-Gavin/llm-tech-report (37 stars, last pushed 20d ago), licensed MIT. It adds 1,353 tokens to every session, about $0.0068 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.