What is syncai AGENTS.md?

Instructions for SyncAI, a Go program that watches and copies configuration between AI coding assistants such as Cursor, Copilot, Claude Code, and Codex. It supports whole files and sets of files matched by patterns.

Building and running the watcher, copying context, ignore, rules, and other agent settings between tools, and performing a manual smoke test in a temporary directory.

It explains how configuration is routed and how to verify changes when the project has no automated test suite.

syncai AGENTS.md — Instructions file for Codex and OpenCode by dmtrkzntsv: Instructions for SyncAI, a Go program that watches and…

Install

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.

agentmods

npx agentmods add instructions/dmtrkzntsv/syncai/agents-md

Clone the repo

git clone --depth 1 https://github.com/dmtrkzntsv/syncai

Made for: 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/dmtrkzntsv/syncai/agents-md.svg)](https://agentmods.dev/instructions/dmtrkzntsv/syncai/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/dmtrkzntsv/syncai/agents-md"><img src="https://agentmods.dev/badge/instructions/dmtrkzntsv/syncai/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,229 This file is loaded in full into every session.

When invoked 1,229 The same file — it is already loaded in full.

Security scan A 1 finding. Scan, not verified.

Origin 100% copy Near-identical to another mod 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	$0.01229	$0.01229
Opus 5	$0.00615	$0.00615
Sonnet 5	$0.00246	$0.00246
Haiku 4.5	$0.00123	$0.00123

Measured 4d ago against content hash 967c45727f89, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

syncai AGENTS.md scanned grade A with 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`.github/workflows/syncai.yml` runs syncai against the repo's own `syncai.json` on every push (except `main` and `release/*`). It builds from source (`make build`) — do **not** reintroduce the cross-repo binary download;

Origin

This is a copy

100% identical to syncai copilot-instructions.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to a Coding Agent when working with code in this repository.

Build & run

make build — go mod tidy then build to bin/syncai.
make run — builds and then runs go run ./cmd -config syncai.json.
make clean — removes bin/.

There is no test suite in this repo (no *_test.go files). Verify changes with make build plus a manual smoke test against a temp working directory:

./bin/syncai -workdir /tmp/syncai-smoke -config /tmp/syncai-smoke/syncai.json -no-watch

CLI flags: -config, -workdir, -no-watch (one-shot for CI), -self-update, -version, -help.

Architecture

SyncAI is a polling watcher that propagates AI-assistant config files between agents (Cursor, Copilot, Claude Code, Codex). The whole program is a single Go binary; the moving parts split cleanly along four "sync kinds" defined in internal/model/model.go:

Kind	Source config field	Source unit	Destination logic
context	`Agent.Context.Path`	single file	verbatim copy
ignore	`Agent.Ignore.Path`	single file	verbatim copy
rules	`Agent.Rules.Pattern`	files matched by glob	content rewritten by per-agent rules generator (frontmatter shape differs between cursor's `globs/alwaysApply` and copilot's `applyTo`)
skills	`Agent.Skills.Pattern`	whole directory matched by glob	every file inside the matched dir copied verbatim, preserving the in-skill relative path

Lifecycle

cmd/main.go loads config, runs initialSync (dedup key kind|stem|rel, picks the newest mtime per logical file across agents), then enters a ticker loop at cfg.Interval() (default 5s).
Each tick rebuilds the watched-file list via (config.Agent).Files() and diffs sha256 hashes against the in-memory filesState. Changes → (*SyncAI).Sync. Missing entries → (*SyncAI).Delete.
Files() uses two distinct collectors: globPattern (file glob, used for rules) and walkSkillDirs (recursive walk of every matched directory, used for skills). Don't conflate them.

Read the full file on GitHub · 70 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.

4d ago First seen · 70 lines · 1,229 tokens per session scan A 967c45727f89

Subscribe to this mod's changes

syncai AGENTS.md is an instructions file published in the GitHub repository dmtrkzntsv/syncai (10 stars, last pushed 4mo ago), licensed MIT. It adds 1,229 tokens to every session, about $0.0061 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to syncai copilot-instructions.md, differing in 0 lines, and is treated as a copy.

Building agents agents claude-code cline copilot cursor cursor-rules

claude-saas-blueprint AGENTS.md

Instructions for GlamgarOnDiscord/claude-saas-blueprint, covering agents.md — claude-saas-blueprint (cross-tool), identity, models (mars 2026), architecture — hexagonale and conventions.

GlamgarOnDiscord/claude-saas-blueprint · 1,069 tokens

agents AGENTS.md

AGENTS.md instructions for commerce-atoms/agents, covering agents.md — @commerce-atoms/agents repo (kit authoring), what this repo is, doctrine for kit authoring and quick reference.

commerce-atoms/agents · 666 tokens

agents CLAUDE.md

Claude Code instructions for commerce-atoms/agents, covering claude.md — @commerce-atoms/agents (kit authoring), behavioural defaults for this repo and where to look.

commerce-atoms/agents · 514 tokens

agents copilot-instructions.md

Copilot instructions for commerce-atoms/agents, covering github copilot — @commerce-atoms/agents (kit authoring) and constraints for autocomplete in this repo.

commerce-atoms/agents · 357 tokens

claude-saas-blueprint CLAUDE.md

Instructions for GlamgarOnDiscord/claude-saas-blueprint, a project described as: Plug-and-play AI workflow that turns Claude Code, Cursor, Copilot or any AI agent into a senior SaaS engineer. Hexagonal architecture, multi-tenant by default, 31 skills + APEX workflow.

GlamgarOnDiscord/claude-saas-blueprint · 1,486 tokens

skill.color-expert CLAUDE.md

Claude Code instructions for meodai/skill.color-expert, covering claude.md, project overview, architecture, no build/test/lint and editing guidelines.

meodai/skill.color-expert · 379 tokens

syncai AGENTS.md