spike

A command that evaluates a software idea before implementation by comparing a full-project view with an independent view that has no project background.

In plain words
What is it for?
For checking whether a proposed design fits the architecture, what may break, and which implementation risks should be considered.
Why use it?
It helps expose weaknesses and convenient assumptions before time is spent building the idea.

Command for Claude Code

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 commands/heznpc/ploidy/spike
Clone the repo
git clone --depth 1 https://github.com/heznpc/PLOIDY

Made for: Claude Code.

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 821 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 $0.00036 $0.00821
Opus 5 $0.00018 $0.00411
Sonnet 5 $0.00007 $0.00164
Haiku 4.5 $0.00004 $0.00082

Measured yesterday against content hash 1ce89669bf1c, 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 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.

.claude/commands/spike.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The user is asking for a pre-implementation gut check on the following idea:

$ARGUMENTS

You hold full project context (repo layout, prior decisions, constraints). That context is exactly what biases you — Ploidy's paper shows that Deep sessions rationalise ideas that fit the existing system even when they are objectively weak. Run the four-step spike without asking the user to confirm.

1 · Write the Deep-context take

In ~200 words, answer these in order:

  1. Fit — does this idea slot cleanly into the existing architecture? Name the concrete touch points.
  2. Implementation risks — what will actually break or be annoying? Be specific (files, components, tests, deploy paths).
  3. Honesty check — what piece of your support for this idea is because it's convenient to build rather than correct? If none, say so explicitly.

Tag every risk / concern HIGH / MEDIUM / LOW. Do not hedge.

2 · Spawn a Fresh sub-agent

Use the Agent tool (subagent_type="general-purpose"). It must see only the idea, not the repo.

Prompt the subagent with exactly:

You have no background about any existing system. Evaluate this idea on its own merits: $ARGUMENTS

Cover in under 200 words:

  1. What problem does this solve? State it in your own words — if you can't, say "unclear".
  2. What assumptions does the idea rely on?
  3. What would make this a bad idea, assuming nothing about the existing stack?

Do not ask for more context. Do not request a repo link.

Capture the subagent's reply as the fresh position.

3 · Converge via Ploidy

Call the debate MCP tool:

debate(
    prompt=$ARGUMENTS,
    mode="solo",
    deep_position=<your step-1 text>,
    fresh_position=<subagent's step-2 text>,
    deep_label="Project-context",
    fresh_label="First-principles",
)

Add a deep_challenge if you found Fresh missing a project-specific constraint. Add a fresh_challenge if Fresh surfaced an assumption you were glossing over. Both optional.

Read the full file on GitHub · 96 lines

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 · 96 lines · 36 tokens per session scan A 1ce89669bf1c

Subscribe to this mod's changes

spike is a command published in the GitHub repository heznpc/PLOIDY (0 stars, last pushed 6d ago), licensed MIT. It adds 36 tokens to every session and 821 once invoked, about $0.0002 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.