spike

spike is a command for coding agents from srstomp/pokayokay. It costs 7 tokens per session (1,097 once invoked), scanned A, original, MIT.

A short, time-limited technical investigation that answers one specific feasibility or design question. It ends with a decision such as proceed, do not proceed, change direction, or gather more information.

In plain words
What is it for?
Use it to check whether an API can be integrated, whether a library fits, or which approach is suitable within a defined time limit.
Why use it?
It limits open-ended investigation and separates answering a question from building the final feature.

Command

Part of the pokayokay plugin — 17 skills, 23 commands, 14 agents, 4 hooks, 1 MCP server shipped together

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/srstomp/pokayokay/spike
Clone the repo
git clone --depth 1 https://github.com/srstomp/pokayokay

Or install pokayokay, the plugin that ships this one along with the rest of its 17 skills, 23 commands, 14 agents, 4 hooks, 1 MCP server.

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/commands/srstomp/pokayokay/spike.svg)](https://agentmods.dev/commands/srstomp/pokayokay/spike)
Your own site
<a href="https://agentmods.dev/commands/srstomp/pokayokay/spike"><img src="https://agentmods.dev/badge/commands/srstomp/pokayokay/spike.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,097 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 $0.00007 $0.01097
Opus 5 $0.00003 $0.00549
Sonnet 5 $0.00001 $0.00219
Haiku 4.5 $0.00001 $0.00110

Measured 3d ago against content hash b7ecfb9f3009, 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 3d 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.

plugins/pokayokay/commands/spike.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spike Investigation Workflow

Investigate: $ARGUMENTS

Agent Delegation

For deep investigations (>1 hour), delegate to the yokay-spike-runner agent for isolated execution. This keeps investigation context separate and allows the agent to write spike reports to .claude/spikes/.

Use the yokay-spike-runner agent to investigate: $ARGUMENTS
Time box: [specify hours]
Return the decision (GO/NO-GO/PIVOT/MORE-INFO) and summary to this conversation.

For quick feasibility checks (<1 hour), run inline without delegation.

Spike Discipline

Spikes answer questions, they don't build features.

Good spike questions:

  • "Can we integrate with X API?"
  • "Is Y library suitable for our use case?"
  • "What's the best approach for Z?"

Bad spike questions:

  • "Build authentication" (that's a feature)
  • "Investigate the codebase" (too vague)
  • "Make it faster" (needs specific question)

Steps

1. Clarify the Question

Reframe $ARGUMENTS as a specific, answerable question.

If vague, ask:

  • What decision does this inform?
  • What would a "yes" answer look like?
  • What would a "no" answer look like?

2. Set Time Box

Duration Use Case
1h Quick feasibility check
2h Standard investigation (default)
4h Complex evaluation
8h Deep dive (requires justification)

3. Create Spike Task

npx @stevestomp/ohno-cli create "Spike: $QUESTION" -t spike
npx @stevestomp/ohno-cli start <task-id>

4. Define Success Criteria

Before starting, document:

## Spike: [Question]
**Time Box**: [hours]
**Started**: [timestamp]
**Must Conclude By**: [timestamp + time-box]

### Success Criteria
- [ ] [Specific criterion 1]
- [ ] [Specific criterion 2]

5. Investigate

Focus on answering the question:

  • Research (docs, examples, community)
  • Proof-of-concept code (if needed)
  • Document findings as you go

6. Checkpoint at 50%

At half time, assess:

## Spike Checkpoint (50%)
**Progress**: [summary of findings so far]
**On Track?**: Yes / No / Pivoting
**Remaining Time**: [hours]

Read the full file on GitHub · 174 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. 3d ago First seen · 174 lines · 7 tokens per session scan A b7ecfb9f3009

Subscribe to this mod's changes

spike is a command published in the GitHub repository srstomp/pokayokay (9 stars, last pushed 2mo ago), licensed MIT. It adds 7 tokens to every session and 1,097 once invoked, about $0.0000 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.