Borrowing it
Nothing to install: this file belongs to abhishekray07/agents-md-templates. 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/abhishekray07/agents-md-templates/main/AGENTS.mdgit clone --depth 1 https://github.com/abhishekray07/agents-md-templatesWrote 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/abhishekray07/agents-md-templates/agents-md)<a href="https://agentmods.dev/instructions/abhishekray07/agents-md-templates/agents-md"><img src="https://agentmods.dev/badge/instructions/abhishekray07/agents-md-templates/agents-md/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.
<a href="https://agentmods.dev/instructions/abhishekray07/agents-md-templates/agents-md"><img src="https://agentmods.dev/badge/instructions/abhishekray07/agents-md-templates/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00591 | $0.00591 |
| Opus 5 | $0.00296 | $0.00296 |
| Sonnet 5 | $0.00118 | $0.00118 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
agents-md-templates 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repo is a starter kit of AGENTS.md templates and per-tool adapters. It is
content (markdown), not an application. This file is the canonical instructions
for any agent working on this repo — and it doubles as a worked example of the
format the templates teach.
Project
agents-md-templates — copy-paste AGENTS.md files and bridges that make one
instruction file work across Claude Code, Codex, Cursor, Gemini CLI, Copilot,
Windsurf, Aider, and the rest. Sibling to claude-md-templates.
Structure
templates/— theAGENTS.mdfiles users copy (global + per-stack)adapters/— bridges that point each tool at the canonicalAGENTS.mdrules/— scoped standards (the cross-tool analogue of Cursor/Windsurf rules)workflows/— tool-agnostic prompts and self-improvement loopsprinciples.md— the research;compatibility.md— the per-tool matrix
Conventions
- Every template must stay lean. A project
AGENTS.mdover ~150 lines starts losing adherence — say so, don't pad. - Keep placeholders in
[square brackets]so they're easy to find and replace. - Use
<!-- HTML comments -->for notes to the human reader. Claude Code strips block-level HTML comments before loading; other tools may keep them, so stay brief. - Prefer "Don't X — do Y instead" over bare prohibitions.
- Every factual claim about a tool's behavior must be traceable to a source in
compatibility.md. If you can't cite it, mark it as community-reported.
Don't
- Don't add formatting rules a linter enforces — that's a linter's job, not the agent's. Mention the linter instead.
- Don't
@-embed long docs into a template — pitch the agent on when to read them. - Don't duplicate the same rule across
AGENTS.mdand a tool-specific adapter. The adapter should referenceAGENTS.md, not copy it.
Verification
This is a docs repo, so "tests" are link and shell checks:
- Run
bash scripts/check.sh— the full harness (shell syntax,setup.shdry-run + real run + idempotency in a temp project, JSON validity, relative link resolution). It must exit 0 before publishing. bash adapters/setup.sh --dry-runfrom a scratch dir should print the bridges it would create without writing anything.- Markdown links should resolve. Relative links point inside the repo; external
links are listed in
README.mdandprinciples.md.
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 · 52 lines · 591 tokens per session scan A 40424f61e0c1
agents-md-templates AGENTS.md is an instructions file published in the GitHub repository abhishekray07/agents-md-templates (2 stars, last pushed 3mo ago), licensed MIT. It adds 591 tokens to every session, about $0.0030 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 2026-08-31.
Other instructions, from other repositories
ruleProb copilot-instructions.md
Instructions for canblmz1/ruleProb, a project described as: Test whether your CLAUDE.md, AGENTS.md and .cursor/rules actually survive AI agent execution. Extract rules, generate sandbox scenarios, score compliance.
agent-rulescope tests.instructions.md
Instructions for 13624725933/agent-rulescope, a project described as: See exactly which instructions your coding agent inherits. Scan AGENTS.md, CLAUDE.md, Cursor and Copilot rules.
agent-rulescope copilot-instructions.md
Copilot instructions for 13624725933/agent-rulescope, a project described as: See exactly which instructions your coding agent inherits. Scan AGENTS.md, CLAUDE.md, Cursor and Copilot rules.
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).