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 skills add stark-ai-de/agent-skills --skill prototype-spikegit clone --depth 1 https://github.com/stark-ai-de/agent-skillsWrote 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/stark-ai-de/agent-skills/prototype-spike)<a href="https://agentmods.dev/skills/stark-ai-de/agent-skills/prototype-spike"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/prototype-spike/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.
<a href="https://agentmods.dev/skills/stark-ai-de/agent-skills/prototype-spike"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/prototype-spike.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00056 | $0.00590 |
| Opus 5 | $0.00028 | $0.00295 |
| Sonnet 5 | $0.00011 | $0.00118 |
| Haiku 4.5 | $0.00006 | $0.00059 |
Grade A, and why
prototype-spike 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 9d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prototype Spike
Goal
Answer a specific uncertainty with a deliberately bounded prototype, then either discard it or convert only the proven idea into production work.
When to use
- The user asks for a spike, proof of concept, prototype, or throwaway experiment.
- A design choice needs evidence before production implementation.
- An integration, API, performance assumption, or UI interaction is uncertain.
When not to use
- The user needs production-ready implementation now.
- The uncertainty can be answered by reading docs or existing code.
- The prototype would require secrets, real customer data, or irreversible operations.
Inputs to inspect
- The exact question the prototype must answer.
- Existing architecture, ADRs, validation commands, and domain docs.
- Constraints on where prototype files may live and how they should be cleaned up.
Workflow
- State the hypothesis or design question.
- Define the prototype boundary, timebox, and throwaway location.
- Ask before adding dependencies, new services, or files outside an agreed scratch area.
- Build the smallest experiment that answers the question.
- Record findings, limitations, and production implications.
- Clean up throwaway files or clearly mark what should remain.
- Recommend whether to proceed, revise, or abandon the production approach.
Safety rules
- Do not ship prototype code as production code without a review step.
- Do not add persistent dependencies or config unless approved.
- Do not use live credentials, customer data, or destructive operations in a spike.
- Do not leave scratch files unmarked or unexplained.
References
No bundled references. Use local ADRs and domain docs when the spike tests an architectural assumption.
Scripts
No bundled scripts.
Output format
Return:
- Question or hypothesis
- Prototype boundary and files touched
- Evidence gathered
- Decision recommendation
- Cleanup performed or remaining
- Production follow-up tasks
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.
- 9d ago First seen · 84 lines · 56 tokens per session scan A 0cb3dca766ba
prototype-spike is a skill published in the GitHub repository stark-ai-de/agent-skills (5 stars, last pushed today), licensed Apache-2.0. It adds 56 tokens to every session and 590 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 2026-08-31.
Other skills, from other repositories
openlore-brainstorm
Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.
openlore-execute-refactor
Apply a confirmed .openlore/refactor-plan.md with a test gate after each change. Use when asked to execute or continue an OpenLore refactoring plan.
openlore-plan-refactor
Identify a high-priority refactoring target, assess its blast radius, and write .openlore/refactor-plan.md without changing code. Use when asked to plan or prioritize a refactor.
openlore-debug
Debug with OpenLore structural context, an explicit root-cause hypothesis, and RED/GREEN verification. Use when a bug, failure, or regression needs diagnosis and repair.
openlore-implement-story
Implement a brownfield story with OpenLore orientation, risk checks, spec validation, tests, and drift detection. Use when asked to implement or continue a story in an existing codebase.
openlore-write-tests
Write and run real tests for a function or spec scenario after reading implementation and contract evidence. Use when asked to add, improve, or repair tests without stubs or placeholders.