tp-spike-auto

tp-spike-auto is a skill for Claude Code from CurtisThe/three-pillars-plugin. It costs 30 tokens per session (1,834 once invoked), scanned A, original, Apache-2.0.

An automated technical-investigation pipeline with an interactive design phase followed by hands-off planning, review, implementation, and results reporting.

In plain words
What is it for?
Use it to explore a technical question under a named design, optionally connect it to a parent design, and produce an implementation decision log.
Why use it?
It lets a spike proceed through its full workflow after the initial design conversation while recording decisions for later human review.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the three-pillars plugin — 37 skills, 20 agents shipped together

Good fit Use it to explore a technical question under a named design, optionally connect it to a parent design, and produce an implementation decision log.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/curtisthe/three-pillars-plugin/tp-spike-auto
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.

Any agent
npx skills add CurtisThe/three-pillars-plugin --skill tp-spike-auto
Clone the repo
git clone --depth 1 https://github.com/CurtisThe/three-pillars-plugin

Made for: Claude Code.

Or install three-pillars, the plugin that ships this one along with the rest of its 37 skills, 20 agents.

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 tp-spike-auto

README.md
[![agentmods](https://agentmods.dev/badge/skills/curtisthe/three-pillars-plugin/tp-spike-auto.svg)](https://agentmods.dev/skills/curtisthe/three-pillars-plugin/tp-spike-auto)
Your own site
<a href="https://agentmods.dev/skills/curtisthe/three-pillars-plugin/tp-spike-auto"><img src="https://agentmods.dev/badge/skills/curtisthe/three-pillars-plugin/tp-spike-auto.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,834 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00030 $0.01834
Opus 5 $0.00015 $0.00917
Sonnet 5 $0.00006 $0.00367
Haiku 4.5 $0.00003 $0.00183

Measured 7d ago against content hash dd095f783a21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

tp-spike-auto 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.

skills/tp-spike-auto/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autonomous Spike Pipeline

Two-phase spike: interactive design conversation, then autonomous execution of the full pipeline. Produces a decision log for human review.

Arguments:

  • {spike-name} (required) — kebab-case name, becomes the directory under three-pillars-docs/tp-designs/.
  • --parent {design-name} (optional) — links this spike to a parent design.

Phase 1: Interactive Design (same as /tp-spike)

  1. Run first-run preflight per skills/_shared/first-run.md.

  2. Validate {spike-name}: must match [a-z0-9-]+.

  3. Resolve the design directory: three-pillars-docs/tp-designs/{spike-name}/. Create if needed.

  4. Run collaboration preflight per skills/_shared/collaboration.md with phase: "design". This is interactive (Phase 1), so prompt the user for branch creation or takeover as described in the shared doc. Honor --force-takeover if passed. Phase 2 will refresh the same lock through each delegated skill.

  5. Check for existing design.md. If exists, ask the user whether to revise or start fresh.

  6. If --parent is given, verify parent design exists and read it.

  7. Have a spike conversation. Draw out through questions:

    • Hypothesis — what do we believe and want to validate?
    • Success criteria — what does GO / PARTIAL / NO-GO look like?
    • Experiments — what will we try, what do we expect to observe?
    • Expected demos — what artifacts prove findings?
    • Constraints — time budget, resource limits, dependencies.
    • Parent linkage — if parent exists, what questions does this spike answer?
  8. Write design.md using the standard spike design format (see /tp-spike for template).

  9. Ask the user: "Design complete. Ready to go autonomous? Once you confirm, I'll run plan → audit → implement → results without stopping. You can review decisions.md in the morning."

    • If the user says no or wants changes, iterate on the design.
    • If the user confirms, proceed to Phase 2.

Read the full file on GitHub · 128 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. 7d ago First seen · 128 lines · 30 tokens per session scan A dd095f783a21

Subscribe to this mod's changes

tp-spike-auto is a skill published in the GitHub repository CurtisThe/three-pillars-plugin (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,834 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-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

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