spike

A time-limited technical experiment used to test whether an uncertain approach will work before committing to a design or implementation. A proof of concept is a small test of feasibility.

In plain words
What is it for?
Use it to test technical assumptions, validate an external API or library feature, prototype an approach, or investigate risky unknowns in a design.
Why use it?
It reduces the risk of building a detailed plan around an untested API, library feature, or integration assumption. The result gives the team evidence before implementation begins.

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/uta2000/feature-flow/spike
Any agent
npx skills add uta2000/feature-flow --skill spike
Clone the repo
git clone --depth 1 https://github.com/uta2000/feature-flow

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,278 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 $0.00072 $0.02278
Opus 5 $0.00036 $0.01139
Sonnet 5 $0.00014 $0.00456
Haiku 4.5 $0.00007 $0.00228

Measured 2d ago against content hash a9ea88db1d16, 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.

skills/spike/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spike / Proof of Concept

Run time-boxed technical experiments to de-risk unknowns before committing to a design or implementation plan. A spike answers the question: "Will this actually work?"

Announce at start: "Running spike to validate technical assumptions before committing to the design."

When to Use

  • Before writing a design document, when technical feasibility is uncertain
  • After brainstorming, when the approach depends on an unverified assumption
  • When a design document references an external API, library feature, or integration pattern that has not been tested
  • When the user explicitly asks to validate something

Project context: Check for .feature-flow.yml in the project root. If found, load the stack entries and check for matching stack-specific assumption patterns at ../../references/stacks/{name}.md. Each stack file includes a "Risky Assumptions (for Spike)" section with common assumptions and how to test them.

Documentation context: If .feature-flow.yml has a context7 field and the Context7 MCP plugin is available (see ../../references/tool-api.md — Context7 MCP Tools for availability check), query relevant Context7 libraries before designing experiments. Current documentation often reveals known limitations, deprecated APIs, or undocumented behaviors that inform what to test. For example, querying Context7 for "Supabase bulk insert limits" before spiking a batch data import can surface rate limits or payload size constraints documented in the official guides.

When to Skip

  • The feature uses only well-understood, previously tested patterns in the codebase
  • All external APIs and libraries are already integrated and used in the same way
  • The unknowns are about UX or product decisions, not technical feasibility

Process

Step 1: Identify Assumptions

Examine the context — either a design document, brainstorming output, or user description — and extract every technical assumption that could fail.

Common categories of risky assumptions:

  • External API behavior: "Gemini can return 100 structured JSON items reliably"
  • Library capabilities: "The installed version of cmdk supports freeform input mode"
  • Performance: "Bulk WHOIS endpoint can handle 500 domains in under 30 seconds"
  • Data format: "The API returns expiration dates in ISO 8601 format"
  • Rate limits: "The free tier allows 100 requests per minute"
  • Integration: "These two libraries work together without conflicts"

Read the full file on GitHub · 195 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 195 lines · 72 tokens per session scan A a9ea88db1d16

Subscribe to this mod's changes

spike is a skill published in the GitHub repository uta2000/feature-flow (4 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 2,278 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens