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/elvisdragonmao/emtech/agents-mdgit clone --depth 1 https://github.com/elvisdragonmao/emtechWrote 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/elvisdragonmao/emtech/agents-md)<a href="https://agentmods.dev/instructions/elvisdragonmao/emtech/agents-md"><img src="https://agentmods.dev/badge/instructions/elvisdragonmao/emtech/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 | $0.00457 | $0.00457 |
| Opus 5 | $0.00229 | $0.00229 |
| Sonnet 5 | $0.00091 | $0.00091 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
emtech 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 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Commit And PR Guidance
Use Linux kernel/Git-style commit subjects with a concrete area, subsystem, component, directory, package, or file prefix:
area: imperative patch summary
sub/sys: imperative patch summary
The prefix should name the repository area primarily changed. Prefer specific prefixes such as a directory, package, file, subsystem, or component name.
Do not use generic Conventional Commit prefixes such as fix:, feat:, chore:, docs:, or refactor: unless they are actual repository areas in this repository. The prefix should describe where the change belongs, not what type of change it is.
Use an imperative verb in the summary after the colon, such as fix, clarify, split, validate, rename, remove, add, update, document, etc. Do not use past tense verbs like fixed or added.
When a patch spans multiple areas, choose the narrowest common area if one exists. If no clear common area exists, use the primary behavior changed rather than listing multiple unrelated prefixes.
The summary after the colon should briefly describe what the patch does, because it becomes the first line shown in the git changelog. Keep it short, imperative, and specific. Prefer subjects under 72 characters. Use lowercase for the first word after the colon unless it is a proper noun, and do not end the subject with a period.
Examples:
storybook: clarify build ownership
web/routes: split route-level chunks
ui/field: fix select menu positioning
server/auth: validate session cookie
githooks.txt: improve the intro section
Use a commit body when the reason for the change is not obvious from the diff. Explain why the change is needed, not just what changed.
PRs should describe the changed area, summarize the user-visible or developer-visible impact, list validation commands run, link related issues, and include screenshots for visible web UI changes.
If no validation was run, state that explicitly and explain why. Do not claim to have run commands that were not actually executed.
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 · 39 lines · 457 tokens per session scan A 1ae7bb7daa4c
emtech AGENTS.md is an instructions file published in the GitHub repository elvisdragonmao/emtech (21 stars, last pushed 6d ago), licensed Apache-2.0. It adds 457 tokens to every session, about $0.0023 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 2026-09-03.
Other instructions, from other repositories
blog CLAUDE.md
Claude Code instructions for gbmhunter/blog, covering units in latex/katex equations, multiplication in latex/katex equations, katex gotchas (beyond units/multiplication above), images and diagrams and mdx components.
daisyui code_generation_with_git.instructions.md
Instructions for saadeghi/daisyui, covering activation, initial setup, development loop, error handling and session end.
planning-with-files AGENTS.md
AGENTS.md instructions for OthmanAdi/planning-with-files, covering agents.md — planning-with-files agent reference card, commit rules, release checklist (12 steps), version bump scope and changelog format.
dario CLAUDE.md
Claude Code instructions for askalf/dario, covering dario — notes for claude code (and other llm coding agents), commits and prs, style, scope and when in doubt, ask.
Commit Message
Comprehensive Conventional Commits guidelines for openwebui-extensions.
ai-git-commiter CLAUDE.md
Instructions for zdt1013/ai-git-commiter, covering ai git commiter, 项目结构, 技术栈, 常用命令 and 安装依赖.