Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/studioKjm/ai-harness-templatenpx agentmods add commands/studiokjm/ai-harness-template/spikeWrote 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/commands/studiokjm/ai-harness-template/spike)<a href="https://agentmods.dev/commands/studiokjm/ai-harness-template/spike"><img src="https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/spike.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.01306 |
| Opus 5 | $0.00014 | $0.00653 |
| Sonnet 5 | $0.00005 | $0.00261 |
| Haiku 4.5 | $0.00003 | $0.00131 |
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 7d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/spike — Time-boxed Investigation
"I don't know yet, and that's the question." — bound the unknown before writing real code.
When to use
- You don't know what to build yet — ouroboros / BMAD-lite require knowing
- You're stuck on a story because of a technical unknown
- You're evaluating a library, API, or architecture choice
- You need real measurements (latency, payload size, behavior)
Not for: implementing known features. Use /decompose (ouroboros) or /story (BMAD-lite) for that.
Usage
/spike new <slug> --question "..." [--timebox 4] [--hypothesis "..."]
/spike list [--status questioning|spiking|learned|applied|abandoned]
/spike show <spike-id>
/spike start <spike-id> # questioning → spiking (timebox starts)
/spike close <spike-id> [--learning-id LN-...] # spiking → learned
/spike abandon <spike-id> --reason "..."
/spike apply <spike-id> # learned → applied (after promotion)
Prerequisites
None. exploration is a base methodology — usable at any point including before /interview.
Instructions
Step 1 — Locate the script
.harness/methodologies/exploration/scripts/spike.py
Step 2 — Run the requested subcommand
Pass through all arguments. Examples:
python3 .harness/methodologies/exploration/scripts/spike.py \
new llm-streaming-vercel \
--question "Can I stream OpenAI tokens through Vercel Edge with TTFT < 300ms?" \
--timebox 4 \
--hypothesis "Yes, using AI SDK + Edge runtime"
Step 3 — Communicate state changes back to the user
The script prints next-step hints. Surface them. Examples:
-
After
new:"Spike
{id}created. Sandbox:{path}. Code in this directory is exempt from layer/spec/structure gates. When you start working, run/spike start {id}to begin the timebox." -
After
start:"Timebox running. Expires at
{expires_at}. At expiry: stop, capture findings via/learn record {id}, then/spike close {id}." -
After
close:"Spike
{id}closed (learned). Findings in{learning_id}.yaml. When ready to apply (ADR / seed update / production code), run/spike apply {id}."
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.
- 7d ago First seen · 126 lines · 27 tokens per session scan A 964b10610116
spike is a command published in the GitHub repository studioKjm/ai-harness-template (43 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 1,306 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 2026-08-30.
Other commands, from other repositories
capture-feedback
Quick feedback capture with structured signals.
check-gates
Run a Pre-Action Gate check against prevention rules before executing a risky action.
show-lessons
Display promoted lessons and their corrective actions.
harness-review
Review the current change set from an opposing harness-engineering perspective.
harness-update
Update a target repository's harness from the latest harness-starter-kit reference material.
harness-doctor
Run Harness Doctor to evaluate how ready the current repository is for reliable AI coding agent collaboration.