skysynth

skysynth is a command for Claude Code from skydiscover-ai/skydiscover. It costs 53 tokens per session (173 once invoked), scanned A, original, Apache-2.0.

A workflow for building a system tailored to a stated workload or formal specification. It studies reference systems, clarifies requirements, builds the system, and checks it with tests or a machine-checked proof.

In plain words
What is it for?
Use it to plan and build specialized software, evaluate its behavior, and add tests for problems found during review.
Why use it?
It provides a structured way to turn an idea into an implemented system while checking correctness and looking for tests that can be accidentally satisfied without solving the real problem.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the skysynth plugin — 2 skills, 1 command, 2 hooks shipped together

Good fit Use it to plan and build specialized software, evaluate its behavior, and add tests for problems found during review.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add skydiscover-ai/skydiscover
Claude Code
/plugin install skysynth

Made for: Claude Code.

Or install skysynth, the plugin that ships this one along with the rest of its 2 skills, 1 command, 2 hooks.

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 skysynth

README.md
[![agentmods](https://agentmods.dev/badge/commands/skydiscover-ai/skydiscover/skysynth/github.svg)](https://agentmods.dev/commands/skydiscover-ai/skydiscover/skysynth)
Your own site
<a href="https://agentmods.dev/commands/skydiscover-ai/skydiscover/skysynth"><img src="https://agentmods.dev/badge/commands/skydiscover-ai/skydiscover/skysynth/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.

agentmods 80×15 button for skysynth

Your own site · 80×15
<a href="https://agentmods.dev/commands/skydiscover-ai/skydiscover/skysynth"><img src="https://agentmods.dev/badge/commands/skydiscover-ai/skydiscover/skysynth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 173 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.00173
Opus 5 $0.00026 $0.00086
Sonnet 5 $0.00011 $0.00035
Haiku 4.5 $0.00005 $0.00017

Measured yesterday against content hash d4fffd420b8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-13, from the pricing page.

Security

Grade A, and why

skysynth 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 yesterday.

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.

skydiscover/synthesize/workflow/adapters/claude/commands/skysynth.md · 16 lines

What it actually says

This file is a thin entry point. The workflow lives at the plugin root, three directories above this file's commands/ directory, beside agents/, references/, and scripts/.

  1. Read ${CLAUDE_PLUGIN_ROOT}/SKILL.md: the lead workflow, its rules, and its references.
  2. Follow it as the lead, with the user's request as the system to synthesize:

$ARGUMENTS

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. yesterday First seen · 16 lines · 53 tokens per session scan A d4fffd420b8e

Subscribe to this mod's changes

skysynth is a command published in the GitHub repository skydiscover-ai/skydiscover (666 stars, last pushed 2d ago), licensed Apache-2.0. It adds 53 tokens to every session and 173 once invoked, about $0.0003 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 2026-09-12.