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.
npx skills add marchatton/agent-skills --skill spike-investigationgit clone --depth 1 https://github.com/marchatton/agent-skillsWrote 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/skills/marchatton/agent-skills/spike-investigation)<a href="https://agentmods.dev/skills/marchatton/agent-skills/spike-investigation"><img src="https://agentmods.dev/badge/skills/marchatton/agent-skills/spike-investigation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/marchatton/agent-skills/spike-investigation"><img src="https://agentmods.dev/badge/skills/marchatton/agent-skills/spike-investigation.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00066 | $0.01010 |
| Opus 5 | $0.00033 | $0.00505 |
| Sonnet 5 | $0.00013 | $0.00202 |
| Haiku 4.5 | $0.00007 | $0.00101 |
Grade A, and why
spike-investigation 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 11d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spike Investigation
Purpose
Turn uncertainty into proof fast.
Based on Shape Up and Ryan Singer's work.
Use spikes to answer “can this be done within the appetite?” with something more concrete than opinions: a small experiment, a thin slice, or a short code sketch that demonstrates the wiring.
Spikes are not mini-projects. They exist to remove a tail of risk.
When to use
- A shaped concept looks plausible but contains rabbit holes (unknowns that could explode the schedule).
- There are technical assumptions that need verification.
- There is a misunderstood dependency or integration boundary.
- A team would otherwise be asked to resolve a hard decision under deadline.
Inputs to request or infer
- Appetite / timebox for shaping and for the eventual build.
- The current concept (breadboard, parts list, fit check).
- The specific risk or question.
- The environment constraints (stack, access, deployment rules).
Workflow
1) Identify rabbit holes
Slow down and review the concept critically.
- Walk through the main use case in slow motion.
- Look for gaps where “something” is assumed to happen.
- Question each element:
- require new technical work?
- depend on a system that isn’t well understood?
- assume a design solution exists?
- hide a hard product/UX decision?
Capture each rabbit hole in a risk list.
Use references/templates/risk-register-template.md.
2) Choose the mitigation move
For each rabbit hole, choose one primary action:
- Patch the hole: dictate a compromise/trade-off that removes uncertainty.
- Declare out of bounds: explicitly say what will not be supported.
- Cut back: drop non-essential flavour that adds tail risk.
- Spike: run an experiment to prove a “straight shot” exists.
Write the decision and why.
3) Define the spike
Specify the spike with tight edges:
- Question: one sentence.
- Success criteria: what proof looks like.
- Timebox: a hard cap.
- Scope: smallest possible slice.
- Artefacts: what to keep (notes, tiny code snippet, diagrams), what to throw away.
What ships with it
5 files 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.
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.
- 11d ago First seen · 132 lines · 66 tokens per session scan A bc68704c352f
spike-investigation is a skill published in the GitHub repository marchatton/agent-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 66 tokens to every session and 1,010 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
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…