What is agent-skills AGENTS.md?

Contributor instructions for a repository containing Openfort skills, which are reusable guides for an AI coding assistant.

Use them when adding or updating Openfort skills, reviewing SDK reference files, or changing the workflow that synchronizes generated documentation.

They clarify the repository layout and identify which files are hand-maintained versus generated from Openfort’s documentation, reducing the risk of editing files that will be overwritten.

How openfort-xyz/agent-skills configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to openfort-xyz/agent-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/openfort-xyz/agent-skills/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/openfort-xyz/agent-skills

Made for: Claude Code, Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/openfort-xyz/agent-skills/agents-md/github.svg)](https://agentmods.dev/instructions/openfort-xyz/agent-skills/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/openfort-xyz/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/openfort-xyz/agent-skills/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/openfort-xyz/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/openfort-xyz/agent-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 663 This file is loaded in full into every session.

When invoked 663 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00663	$0.00663
Opus 5	$0.00331	$0.00331
Sonnet 5	$0.00133	$0.00133
Haiku 4.5	$0.00066	$0.00066

Measured 9d ago against content hash 552e055767a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agent-skills 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.

AGENTS.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instructions for AI Agents

This repository contains Agent Skills for the Openfort platform.

Repository Structure

skills/
├── openfort/           — General Openfort platform skill (MCP tools + docs navigation)
├── openfort-cli/       — Openfort CLI skill (command-line operations)
├── embedded-wallet/    — Embedded wallet skill (client-side wallets for React, React Native, Swift, Unity, JS)
└── backend-wallet/     — Backend wallet skill (server-side wallets for EVM and Solana)

Skill Format

Each skill follows the Agent Skills standard:

SKILL.md — Main skill file with YAML frontmatter (name, description, metadata, inputs, references) and markdown body
references/ — Supporting detail documents referenced by the SKILL.md

Source of truth — what is hand-edited vs. generated

The per-SDK reference files are generated from the Openfort documentation (openfort.io/docs, source: openfort-xyz/documentation → public/skills/). A GitHub Action (.github/workflows/sync-skills.yml, via scripts/sync-skills.mjs) copies them in. Do not hand-edit the generated files — fix the content in the documentation repo and let the sync carry it here.

File	Source	Edit where
`embedded-wallet/references/openfort-{js,react,react-native,swift,unity}.md`	docs `public/skills/`	docs repo (generated here)
`backend-wallet/references/setup.md`	docs `public/skills/openfort-backend-wallet-setup.md`	docs repo (generated here)
`backend-wallet/references/{evm-wallets,solana-wallets,fee-sponsorship,policy-engine}.md`	—	this repo (native)
`openfort/references/mcp-tools.md`	—	this repo (native)
all `SKILL.md` wrappers	—	this repo (native)

Editing the hand-maintained (native) files

When editing a native SKILL.md or reference, preserve the YAML frontmatter structure
When adding a new native reference file, also add it to the references list in the parent SKILL.md frontmatter
Each SKILL.md must declare a unique name in its frontmatter
Keep SKILL.md focused on overview, routing, and quick-start. Move detailed API docs to references/
Test that frontmatter parses correctly (valid YAML between --- delimiters)

Read the full file on GitHub · 57 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.

9d ago First seen · 57 lines · 663 tokens per session scan A 552e055767a4

Subscribe to this mod's changes

agent-skills AGENTS.md is an instructions file published in the GitHub repository openfort-xyz/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 663 tokens to every session, about $0.0033 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.

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

agent-skills: Instructions file for Claude Code