discovery-methodology

discovery-methodology is a skill for Claude Code from HartBrook/trailhead. It costs 25 tokens per session (917 once invoked), scanned A, original, MIT.

A structured process for discovering and recording the architecture of a new software project. It guides a developer from an initial idea through requirements and design decisions.

In plain words
What is it for?
Use it to explore a new project, ask the right requirements questions, define measurable needs, and document architectural choices before implementation.
Why use it?
It prevents choosing technologies before understanding the problem and turns vague needs into specific, reviewable requirements. It also keeps architecture discussions focused and organized.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the trailhead plugin — 2 skills shipped together

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/hartbrook/trailhead/discovery-methodology
Any agent
npx skills add HartBrook/trailhead --skill discovery-methodology
Clone the repo
git clone --depth 1 https://github.com/HartBrook/trailhead

Made for: Claude Code.

Or install trailhead, the plugin that ships this one along with the rest of its 2 skills.

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 discovery-methodology

README.md
[![agentmods](https://agentmods.dev/badge/skills/hartbrook/trailhead/discovery-methodology.svg)](https://agentmods.dev/skills/hartbrook/trailhead/discovery-methodology)
Your own site
<a href="https://agentmods.dev/skills/hartbrook/trailhead/discovery-methodology"><img src="https://agentmods.dev/badge/skills/hartbrook/trailhead/discovery-methodology.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 917 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 $0.00025 $0.00917
Opus 5 $0.00013 $0.00458
Sonnet 5 $0.00005 $0.00183
Haiku 4.5 $0.00003 $0.00092

Measured 5d ago against content hash c0ab5ba9d0b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

discovery-methodology 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.

src/skills/discovery-methodology/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Discovery Methodology

A structured process for turning "I need to build X" into a documented set of architectural decisions. The value is in the questions, not the answers — the developer has domain expertise, this process provides process expertise.

The 7 Principles

  1. Problem before solution — Requirements before technology. Always. If a developer leads with a technology preference, acknowledge it, park it, and redirect to requirements first.

  2. One question at a time — Use AskUserQuestion for structured choices (e.g., selecting from consistency models). Use open-ended prose for exploratory topics (e.g., "Walk me through what happens when a user first signs up").

  3. Drive, don't follow — The process owns the conversation structure. Announce the current phase, explain why it matters, guide the developer through it. They provide answers; you provide the framework.

  4. Challenge vague answers — "Fast" is not a requirement. "p95 under 200ms for search queries" is. Push for specifics: which dimension, what numbers would be uncomfortable.

  5. Respect expertise — Collaborative senior architect, not interviewer. If the developer clearly has deep knowledge, skip the basics. If they are junior, provide context on why each question matters.

  6. Ground in reality — Use WebSearch for technology comparisons. Don't rely on training data for version numbers, pricing, ecosystem status, or maturity.

  7. Make it resumable — Update discovery-state.md after each phase so sessions can be interrupted and continued.

The 6 Phases

Phase 1: Problem Framing

Extract the problem at the problem level, not the solution level. Output: problem statement (2-3 sentences), measurable success criteria.

Phase 2: Functional Requirements

Map capabilities, workflows, data, and interactions. Surface implicit requirements by asking about edge cases, failure scenarios, and integration points.

Phase 3: Non-Functional Requirements

Structured walkthrough of 5 dimensions:

  • Scale & Performance — users, latency, throughput, burst patterns
  • Availability & Reliability — downtime cost, uptime target, RPO/RTO, graceful degradation
  • Data & Consistency — consistency model, retention, regulatory, auditability
  • Security & Compliance — auth model, sensitive data, regulatory requirements
  • Team & Operational — team size, known tech, deployment, on-call maturity, budget

Read the full file on GitHub · 66 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 · 66 lines · 25 tokens per session scan A c0ab5ba9d0b3

Subscribe to this mod's changes

discovery-methodology is a skill published in the GitHub repository HartBrook/trailhead (6 stars, last pushed 6mo ago), licensed MIT. It adds 25 tokens to every session and 917 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 2026-08-31.

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