spike

An exploratory coding command used to understand a problem before building the final solution. It follows TDD, a method of using tests to guide development, but its purpose is investigation rather than finished code.

In plain words
What is it for?
Use it for small experiments, technical investigations, and checking possible approaches before implementation. It can also use the conversation context or available task-tracking work when no specific problem is supplied.
Why use it?
It reduces uncertainty when the requirements or technical approach are unclear. Developers can learn about the problem space before committing to a design.

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/wbern/agent-instructions/spike
Clone the repo
git clone --depth 1 https://github.com/wbern/agent-instructions

Made for: Claude Code.

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,231 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 89% copy Near-identical to another mod 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 $0.00015 $0.01231
Opus 5 $0.00008 $0.00616
Sonnet 5 $0.00003 $0.00246
Haiku 4.5 $0.00002 $0.00123

Measured 2d ago against content hash e9094db2ed97, 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 2d 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.

Origin

This is a copy

89% identical to cycle — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/spike.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User arguments:

Spike: $ARGUMENTS

End of user arguments

SPIKE PHASE! Apply the below to the user input above.

General Guidelines

Output Style

  • Never explicitly mention TDD in code, comments, commits, PRs, or issues
  • Write natural, descriptive code without meta-commentary about the development process
  • The code should speak for itself - TDD is the process, not the product

Beads is available for task tracking. Use mcp__beads__* tools to manage issues (the user interacts via bd commands).

Plan File Restriction

NEVER create, read, or update plan.md files. Claude Code's internal planning files are disabled for this project. Use other methods to track implementation progress (e.g., comments, todo lists, or external tools).

(If there was no info above, fallback to:

  1. Context of the conversation, if there's an immediate thing
  2. bd ready to see what to work on next and start from there)

TDD Fundamentals

The TDD Cycle

The foundation of TDD is the Red-Green-Refactor cycle:

  1. Red Phase: Write ONE failing test that describes desired behavior

    • The test must fail for the RIGHT reason (not syntax/import errors)
    • Only one test at a time - this is critical for TDD discipline
      • Exception: For browser-level tests or expensive setup (e.g., Storybook *.stories.tsx), group multiple assertions within a single test block to avoid redundant setup - but only when adding assertions to an existing interaction flow. If new user interactions are required, still create a new test. Split files by category if they exceed ~1000 lines.
    • Adding a single test to a test file is ALWAYS allowed - no prior test output needed
    • Starting TDD for a new feature is always valid, even if test output shows unrelated work
    • For DOM-based tests, use data-testid attributes to select elements rather than CSS classes, tag names, or text content
    • Avoid hard-coded timeouts both in form of sleep() or timeout: 5000 etc; use proper async patterns (waitFor, findBy*, event-based sync) instead and rely on global test configs for timeout settings

Read the full file on GitHub · 115 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. 2d ago First seen · 115 lines · 15 tokens per session scan A e9094db2ed97

Subscribe to this mod's changes

spike is a command published in the GitHub repository wbern/agent-instructions (168 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 1,231 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to cycle, differing in 8 lines, and is treated as a copy.