write-spike

write-spike is a skill for Claude Code, Codex from cpliakas/claude-code-engineering-leaders. It costs 41 tokens per session (1,065 once invoked), scanned A, original, MIT.

A structured investigation document for work that is too uncertain to turn directly into a user story. It records the problem, key questions, options, findings, unknowns, and a possible starting point for later development work.

In plain words
What is it for?
Use it to research an unclear feature or technical decision, compare options, document what is known, identify follow-up questions, and prepare a well-defined user story.
Why use it?
It prevents teams from writing detailed requirements before they understand the problem or available choices. It also makes unresolved assumptions visible and sets a time limit for investigation.

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/cpliakas/claude-code-engineering-leaders/write-spike
Any agent
npx skills add cpliakas/claude-code-engineering-leaders --skill write-spike
Clone the repo
git clone --depth 1 https://github.com/cpliakas/claude-code-engineering-leaders

Made for: Claude Code, Codex.

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 write-spike

README.md
[![agentmods](https://agentmods.dev/badge/skills/cpliakas/claude-code-engineering-leaders/write-spike.svg)](https://agentmods.dev/skills/cpliakas/claude-code-engineering-leaders/write-spike)
Your own site
<a href="https://agentmods.dev/skills/cpliakas/claude-code-engineering-leaders/write-spike"><img src="https://agentmods.dev/badge/skills/cpliakas/claude-code-engineering-leaders/write-spike.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,065 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 5.1 $0.00041 $0.01065
Opus 5 $0.00020 $0.00532
Sonnet 5 $0.00008 $0.00213
Haiku 4.5 $0.00004 $0.00106

Measured 5d ago against content hash 010b752b3587, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

write-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 5d 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/write-spike/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Spike

Produce a structured findings document that resolves enough uncertainty to let the product owner write a well-formed user story.

Input

$ARGUMENTS = the topic, question, or work area that is too uncertain to story-write directly.

Process

1. Gather Context

  • Read the project's CLAUDE.md for architecture, domain language, and constraints
  • Scan for a roadmap or backlog file if one exists (Glob for roadmap*, backlog*, TODO*)
  • Identify any existing work or decisions that bear on the topic

2. Scope the Investigation

State clearly:

  • The driving question: What specific question does this spike need to answer? Narrow to one well-formed question if the input is broad.
  • Why now: What decision or story is blocked until this question is answered?
  • Out of scope: What related questions will be explicitly deferred?
  • Timebox: State a recommended investigation timebox (typically 1-2 days for a focused spike). The spike should produce findings within this window even if not all questions are fully resolved — partial findings with identified follow-ups are better than an unbounded investigation.

A spike that tries to answer three questions usually answers none well.

3. Explore the Topic

Research the topic through whatever means are available:

  • Read relevant source files if the topic is code or architecture
  • Search for documentation, prior art, or established patterns (WebSearch / WebFetch)
  • Enumerate options or approaches with concrete trade-offs — not just "Option A vs Option B" but specific pros, cons, and constraints for this project
  • Note sources and links for evidence that will be referenced in the output

When options involve architectural trade-offs (one-way doors, pattern selection, service boundaries), note that the findings should be reviewed by the Chief Architect before being used to seed a story. The spike documents options; architectural judgment belongs to the Chief Architect.

4. Assess Story Readiness

Read the full file on GitHub · 114 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. 5d ago First seen · 114 lines · 41 tokens per session scan A 010b752b3587

Subscribe to this mod's changes

write-spike is a skill published in the GitHub repository cpliakas/claude-code-engineering-leaders (4 stars, last pushed 14d ago), licensed MIT. It adds 41 tokens to every session and 1,065 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.

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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens