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.
npx agentmods add skills/sjarmak/agent-workflows/crossbreednpx skills add sjarmak/agent-workflows --skill crossbreedgit clone --depth 1 https://github.com/sjarmak/agent-workflowsWrote 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/skills/sjarmak/agent-workflows/crossbreed)<a href="https://agentmods.dev/skills/sjarmak/agent-workflows/crossbreed"><img src="https://agentmods.dev/badge/skills/sjarmak/agent-workflows/crossbreed.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02074 |
| Opus 5 | $0.00000 | $0.01037 |
| Sonnet 5 | $0.00000 | $0.00415 |
| Haiku 4.5 | $0.00000 | $0.00207 |
Grade A, and why
crossbreed 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 5d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structural recombination of existing designs. Takes 2-3 prototypes or design approaches and spawns N agents to create HYBRID designs, each with a different "dominant parent" whose architecture leads while grafting specific elements from the others.
Arguments
$ARGUMENTS — format: [N] path1 path2 [path3] where N is optional number of hybrid agents (default: one per parent, min 2, max 5) and paths point to prototype branches, design docs, or PROTOTYPE_NOTES.md files
Parse Arguments
Extract:
- agent_count: optional leading integer (default: one per parent path, min 2, max 5)
- parent_paths: 2-3 paths to prototype branches, design docs, or PROTOTYPE_NOTES.md files
Validate:
- At least 2 parent paths are provided
- No more than 3 parent paths
- Each path exists and contains readable design material (code, docs, or PROTOTYPE_NOTES.md)
Phase 1: Analyze the Parents
For each parent design:
- Read the design doc, code, or prototype notes at the given path
- Extract structural elements:
- Architecture pattern (monolith, modular, layered, event-driven, etc.)
- Data model and state management approach
- Key algorithms or core logic
- API design and interface boundaries
- Dependency choices (libraries, frameworks)
- Error handling strategy
- File organization and module structure
- Identify what this parent does BEST — its distinctive strength
- Identify what this parent does WORST or leaves incomplete
Present a parent comparison table to the user:
| Element | Parent A | Parent B | Parent C |
|---|---|---|---|
| Architecture | ... | ... | ... |
| Data model | ... | ... | ... |
| Key algorithm | ... | ... | ... |
| API design | ... | ... | ... |
| Dependencies | ... | ... | ... |
| Error handling | ... | ... | ... |
| Distinctive strength | ... | ... | ... |
| Weakness / gap | ... | ... | ... |
Ask the user to confirm which elements they want to see recombined before proceeding.
Phase 2: Design Recombination Strategies
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.
- 5d ago First seen · 204 lines · 0 tokens per session scan A 121f23353563
crossbreed is a skill published in the GitHub repository sjarmak/agent-workflows (9 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,074 tokens. 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 skills, from other repositories
ui-design-source
Use this skill when the user provides Figma material, design-export files, screenshots of design tools, PDFs, JSON, existing HTML, or asks for design-to-HTML/code fidelity. It adapts OpenDesign/Figma handoff discipline for UIDesigner without requiring a live Figma runtime.
design-system-importer
Use this when COMPOSE or an AUTO compose segment has any external reference media or style source: a reference image, reference video, DESIGN.md, brand guide, screenshot, existing website, design notes, or an explicit named visual direction.
ui-design-system
Use this skill when creating, extending, or auditing a product UI system. It adapts Better Design-style design-system discipline without requiring an external runtime package.
ui-reference-packs
Use this skill after ui-design-contract only when UIDesigner needs a visual-system reference, product pattern, or style benchmark. It adapts OpenDesign's design-system and template catalogue into a small routed reference layer for HTML-first UI work.
composition-design-review
Apply this checklist yourself after a successful composition.snapshot, before the preview is shown. It is advisory: nothing is submitted to the host, no operation records a verdict, and no gate waits on it — the host publishes the contact sheet with the passing snapshot. It is a design QA layer for your own authoring…
ui-controls-accessibility
Before rendering, turn every explicitly requested workflow outcome into a compact ledger: user outcome -> triggering control/event -> rendered state branch -> recovery/next action. Success and failure are separate outcomes. When a backend is unavailable but the outcome can be modeled locally, make both outcomes…