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/diverge-prototypenpx skills add sjarmak/agent-workflows --skill diverge-prototypegit 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/diverge-prototype)<a href="https://agentmods.dev/skills/sjarmak/agent-workflows/diverge-prototype"><img src="https://agentmods.dev/badge/skills/sjarmak/agent-workflows/diverge-prototype.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 | $0.01769 |
| Opus 5 | $0.00000 | $0.00885 |
| Sonnet 5 | $0.00000 | $0.00354 |
| Haiku 4.5 | $0.00000 | $0.00177 |
Grade A, and why
diverge-prototype 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 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.
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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Divergent prototyping. Spawns N independent agents in isolated worktrees to explore different implementation approaches for a PRD, then synthesizes results.
Arguments
$ARGUMENTS — format: [N] [path/to/prd.md] where N is optional (default: 3) and PRD path is optional
Parse Arguments
Extract:
- agent_count: optional leading integer (default 3, min 2, max 7)
- prd_path: optional path to an existing PRD markdown file
Phase 0: Ensure PRD Exists
If a PRD path is provided: read and validate it. It should contain at minimum: Problem Statement, Goals, and Requirements sections. If it's missing key sections, work with the user to fill gaps.
If no PRD path is provided: tell the user they need a PRD first and offer two options:
- Run
/divergeto research the topic and generate one - Collaborate right now to draft a quick PRD interactively
If they choose option 2, walk through these questions:
- What problem are we solving?
- What does success look like?
- What are the must-have requirements?
- What are the constraints (tech stack, compatibility, performance)?
- What are the non-goals?
Save the resulting PRD to prd_{topic}.md and confirm with the user before proceeding.
Phase 1: Design Exploration Strategies
Based on the PRD requirements, design N distinct implementation strategies. Each strategy should:
- Take a meaningfully different architectural or technical approach
- Be feasible given the constraints
- Cover different points in the trade-off space (e.g., simplicity vs flexibility, speed vs correctness)
Examples of strategy differentiation:
- "Minimal viable approach" — least code, fastest to ship
- "Framework-heavy approach" — leverage existing libraries/patterns
- "Performance-first approach" — optimize for speed/scale
- "Extensibility-first approach" — optimize for future changes
- "Unconventional approach" — novel technique or pattern
Present the strategies to the user and get confirmation before spawning agents.
Phase 2: Spawn Prototype Agents
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 · 173 lines · 0 tokens per session scan A 7e0e76da99f2
diverge-prototype 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 1,769 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
speckit.specify
Skill "speckit.specify" from caipe-io/ai-platform-engineering, covering user input, outline, quick guidelines, section requirements and for ai generation.
speckit.clarify
Skill "speckit.clarify" from caipe-io/ai-platform-engineering, covering user input and outline.
local-integration-testing
Run end-to-end integration tests with all 15 agents and supervisor in local Docker Compose dev environment. Validates agent discovery, multi-agent routing, checkpoint persistence, and cross-agent follow-up conversations.
release-docs
Generate a combined release blog post for ai-platform-engineering. Produces a single docs/releases/YYYY-MM-DD-release-X-Y-Z.md file containing release notes and the upgrade guide (migration guide) inline. Use when cutting a release, when a user asks "what changed in 0.4.x", or when upgrading their values.yaml to a new…
update-docs
Audit and update all documentation moving parts for ai-platform-engineering. Checks release blog posts, features page, agent docs, homepage version strings, Docusaurus version config, and sidebar completeness. Fixes what is stale and reports what needs manual attention. Use after cutting a release, adding a new agent…
docker-compose-first-install
Validate and repair the OSS first-install Docker Compose path. Use when editing docker-compose.yaml, docker-compose.dev.yaml, .env.example, release image tags, Compose profiles, Keycloak/OpenFGA/RAG defaults, or first-launch UI behavior for local all-in-one installs.