Borrowing it
Nothing to install: this file belongs to kltsv/ai-vendor-agnostic-setup. 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/kltsv/ai-vendor-agnostic-setup/main/AGENTS.mdgit clone --depth 1 https://github.com/kltsv/ai-vendor-agnostic-setupWrote 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/kltsv/ai-vendor-agnostic-setup/agents-md)<a href="https://agentmods.dev/instructions/kltsv/ai-vendor-agnostic-setup/agents-md"><img src="https://agentmods.dev/badge/instructions/kltsv/ai-vendor-agnostic-setup/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/kltsv/ai-vendor-agnostic-setup/agents-md"><img src="https://agentmods.dev/badge/instructions/kltsv/ai-vendor-agnostic-setup/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 | $0.00611 | $0.00611 |
| Opus 5 | $0.00305 | $0.00305 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
ai-vendor-agnostic-setup 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 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guide
This repository is a vendor-agnostic agent harness: one source of truth in
.agents/, compiled into each AI coding agent's native config. The repo is
the example — there is no separate product.
Source of truth — .agents/
Everything agent-related is authored here:
.agents/permissions.toml— permission intent (allow / ask / deny).agents/hooks.toml— hook intent, with{file}/{repo_root}placeholders.agents/skills/<name>/SKILL.md— skill sources (one dir per skill).agents/setup.py— the compiler that emits the per-vendor configs
Generated mirrors — gitignored, read-only, do not edit: .claude/,
.codex/, and the root CLAUDE.md (a @AGENTS.md shim so Claude Code inlines
this file).
Editing any mirror is wasted work: the next compile overwrites it. All changes
go in .agents/ or AGENTS.md. Mirrors stay fresh automatically — a
session_start hook runs .agents/setup.py each session. Manual check:
python3 .agents/setup.py --check (non-zero exit if a mirror is stale).
Bootstrap on a fresh clone
Mirrors are gitignored, so a fresh clone has none — including the hook that keeps them fresh. Run the compiler once after cloning; it self-maintains afterward:
python3 .agents/setup.py
Requires Python 3.11+ (stdlib tomllib, no dependencies).
How to change things
- Permissions — edit
.agents/permissions.toml, then recompile. - Hooks — edit
.agents/hooks.toml. Use{file}/{repo_root}placeholders; a hook with a placeholder a vendor can't map is omitted for that vendor, not emitted with a guess. - Skills — add
.agents/skills/<name>/SKILL.md(plus any sibling files); they're mirrored verbatim into every vendor. Deleting a source removes its mirrors on the next compile. - A new vendor — see
docs/adding-a-vendor.md.
Conventions
- Directory docs are
AGENTS.md, notREADME.md.README.mdexists only at the root (the human front door). Subdirectories useAGENTS.md. - Commits — see the
commitskill: small, logical, known-good chunks.
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.
- 9d ago First seen · 59 lines · 611 tokens per session scan A d68607fe0ee2
ai-vendor-agnostic-setup AGENTS.md is an instructions file published in the GitHub repository kltsv/ai-vendor-agnostic-setup (5 stars, last pushed 2mo ago), licensed MIT. It adds 611 tokens to every session, about $0.0031 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
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.