spike

spike is a skill for Claude Code, Codex from New1Direction/korgex. It costs 18 tokens per session (283 once invoked), scanned A, original, MIT.

A time-limited throwaway experiment used to answer an uncertain technical question before building the real solution.

In plain words
What is it for?
Use it to test whether an API or design approach is viable, record what you learned, delete the experiment, and then build the proper solution with TDD.
Why use it?
It separates learning from production code, so rushed experiments and their hidden assumptions do not become the final implementation.

Skill for Claude CodeCodex

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 skills/new1direction/korgex/spike
Any agent
npx skills add New1Direction/korgex --skill spike
Clone the repo
git clone --depth 1 https://github.com/New1Direction/korgex

Made for: Claude Code, Codex.

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 spike

README.md
[![agentmods](https://agentmods.dev/badge/skills/new1direction/korgex/spike.svg)](https://agentmods.dev/skills/new1direction/korgex/spike)
Your own site
<a href="https://agentmods.dev/skills/new1direction/korgex/spike"><img src="https://agentmods.dev/badge/skills/new1direction/korgex/spike.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 283 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00018 $0.00283
Opus 5 $0.00009 $0.00142
Sonnet 5 $0.00004 $0.00057
Haiku 4.5 $0.00002 $0.00028

Measured 5d ago against content hash 601f7a5dd881, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

src/skills_builtin/spike/SKILL.md · 25 lines

What it actually says

A spike is a time-boxed experiment to answer a question ("does this API work like I think?", "is this approach viable?"). Its only output is knowledge — the code is disposable.

  1. State the question. Write down exactly what you're trying to learn. The spike is done when it's answered, not when the code "works".
  2. Go fast and dirty. Skip tests, error handling, and polish. Hardcode. The point is to learn, not to ship — don't invest in code you'll throw away.
  3. Time-box it. Set a bound. If you blow past it, you've learned the problem is harder than expected — that's itself an answer; report it.
  4. Capture the finding. Record what you learned (and consider saving it as a skill or memory if it'll recur).
  5. THROW THE CODE AWAY. Delete the spike. Then build the real thing from scratch with test-driven-development — do NOT "clean up" the spike into production code; it carries hidden assumptions and skipped cases.

Red flag: a spike quietly becoming the implementation. Delete means delete.

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. 5d ago First seen · 25 lines · 18 tokens per session scan A 601f7a5dd881

Subscribe to this mod's changes

spike is a skill published in the GitHub repository New1Direction/korgex (5 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 283 once invoked, about $0.0001 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.