skills AGENTS.md

skills AGENTS.md is an instructions file for Codex, OpenCode from sivi/skills. It costs 2,708 tokens per session, scanned B, original, MIT.

Repository instructions for AI-agent skills that create design assets and manage brand-marketing campaigns through the Sivi API. They describe a three-layer structure, including setup, individual API jobs, and workflows that combine several jobs.

In plain words
What is it for?
Use them when setting up Sivi, configuring its API key, creating brand context, or developing skills for generating design assets and marketing campaigns.
Why use it?
They clarify the order in which shared configuration and brand context must be prepared before using design or media skills. They also explain how the repository avoids duplicating shared settings.

Instructions file for CodexOpenCode

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/sivi/skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/sivi/skills

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.

agentmods badge for skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sivi/skills/agents-md.svg)](https://agentmods.dev/instructions/sivi/skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sivi/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/sivi/skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,708 This file is loaded in full into every session.
When invoked 2,708 The same file — it is already loaded in full.
Security scan B 2 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.02708 $0.02708
Opus 5 $0.01354 $0.01354
Sonnet 5 $0.00542 $0.00542
Haiku 4.5 $0.00271 $0.00271

Measured 4d ago against content hash 5fd5e1baf045, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

skills AGENTS.md scanned grade B with 2 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 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

The body is markdown documentation that agents consume to learn the API workflow, including step-by-step bash script templates, argument parsing rules, error handling, and result display instructions.

Makes network callslowCapability

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

- **Cross-platform**: Scripts must work on macOS, Linux, and Windows (Git Bash / WSL). Never use `head -n -1` or `jq`. Use `python3` for JSON parsing and `curl -o` for response handling.
AGENTS.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This file provides guidance to AI agents when working with code in this repository.

Overview

This is a skills repository for AI agents (Claude Code, Cursor, Copilot, Windsurf, Cline, etc.) to generate production-ready design assets and manage brand marketing campaigns using the Sivi API. It contains no application code — only skill definition files (SKILL.md) that teach AI agents how to call the Sivi Core API via bash scripts.

Skills are installed by users via npx skills add sivi/skills (see skills.sh).

Skill System Architecture

Skills are organized in three layers:

Layer 0 — Foundation

  • setup-sivi — One-time setup and the shared home. Creates the single .env (captures SIVI_API_KEY) and owns the _shared/ reference files. Every other skill resolves this folder at runtime as $SIVI_HOME and sources its .env — no copies. Run this before any design/media skill.
  • brand-context (coming soon) — Creates a brand profile via two paths: (A) extract from a URL, or (B) create from name + description. Checks Sivi workspace for existing brands before creating. Registers with Sivi, creates brands/<slug>/brand.md. All other skills depend on this.

Layer 1 — Atomic engines (single API job)

  • generate-design — Orchestrates the full design workflow: copy generation (step 2.2, optional) → media enhancement (step 3.2, optional) → image generation (step 3.3, when no assets provided) → design generation. Supports both designs-from-content (copy-first, pixel-faithful text) and designs-from-prompt (direct generation, no copy review). The core execution engine. Uses _shared/submit-and-poll-content.sh (default) and _shared/submit-and-poll-prompt.sh (alternative) as its submit/poll templates.
  • write-copy — Standalone copy-only skill. Generates 2 copy variations (agent-generated, no API). For users who want copy without design generation.
  • enhance-media — AI image generation and enhancement.
  • handle-media — Lightweight image resolver: resolves any of 4 sources (local file, direct image URL, product/webpage URL auto-pick, AI generation) into a Sivi mId/mediaUrl. Used by composite skills to avoid duplicating media handling scripts. No brand required, no save-to-folder.
  • brand-assets (coming soon) — Brand-scoped asset manager: uploads local files to Sivi via presigned URL, registers remote/product/webpage URLs, and saves references in the brand's assets folder. Requires brand association. For lightweight resolution without brand, see handle-media.
  • manage-brand (coming soon) — List, update, switch, or archive brands.

Read the full file on GitHub · 140 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.

  1. 4d ago First seen · 140 lines · 2,708 tokens per session scan B 5fd5e1baf045

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository sivi/skills (2 stars, last pushed 25d ago), licensed MIT. It adds 2,708 tokens to every session, about $0.0135 per session on Opus 5. A static security scan graded it B with 2 findings (asks the agent to reveal its instructions, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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 · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js 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