trailhead

trailhead is a skill for Claude Code from HartBrook/trailhead. It costs 14 tokens per session (3,557 once invoked), scanned A, original, MIT.

A guided architecture-discovery session for a new software project. It leads a developer through six phases to clarify requirements, compare technologies, and record decisions before coding.

In plain words
What is it for?
Use it to plan a greenfield project, explore technology choices, document architecture decisions, and resume an existing discovery session.
Why use it?
It helps uncover important project details early, when architecture changes are easier to make.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; names the TodoWrite tool.

Part of the trailhead plugin — 2 skills shipped together

Good fit Use it to plan a greenfield project, explore technology choices, document architecture decisions, and resume an existing discovery session.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hartbrook/trailhead/trailhead
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 HartBrook/trailhead --skill trailhead
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 trailhead

README.md
[![agentmods](https://agentmods.dev/badge/skills/hartbrook/trailhead/trailhead/github.svg)](https://agentmods.dev/skills/hartbrook/trailhead/trailhead)
Your own site
<a href="https://agentmods.dev/skills/hartbrook/trailhead/trailhead"><img src="https://agentmods.dev/badge/skills/hartbrook/trailhead/trailhead/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.

agentmods 80×15 button for trailhead

Your own site · 80×15
<a href="https://agentmods.dev/skills/hartbrook/trailhead/trailhead"><img src="https://agentmods.dev/badge/skills/hartbrook/trailhead/trailhead.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,557 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 $0.00014 $0.03557
Opus 5.5 $0.00006 $0.01423
Sonnet 5.5 $0.00003 $0.00711
Haiku 4.5 $0.00001 $0.00356

Measured 2mo ago against content hash c7631acea929, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

trailhead 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 2mo 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/trailhead/SKILL.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trailhead: Architecture Discovery

You are a senior software architect conducting a collaborative architecture discovery session. You guide a developer through a structured 6-phase process that uncovers requirements, explores technology options, and documents decisions — before any code is written.

Tagline: Know the terrain before you commit to the trail.

Phase 0: Setup

Parse arguments

The user may pass arguments after the command name. The raw argument string is:

$ARGUMENTS

If the argument string is empty or blank, use all defaults. Extract key=value pairs from the string. Any remaining text that is not a key=value pair is treated as the project description.

Key Default Description
output planning/ Directory for discovery state and output files

Log the resolved configuration:

Trailhead Configuration:
  output:      <resolved value>
  description: <resolved value or "none — will discover interactively">

Detect existing session

Check if <output>/discovery-state.md exists:

  • If it exists: Read it and present the current state to the developer. Ask whether they want to resume from the last completed phase or start fresh. If resuming, skip to the next incomplete phase and use the accumulated context from the state file.
  • If it does not exist: Create the output directory if needed. This is a new session.

Initialize state

For new sessions, create <output>/discovery-state.md with:

# Trailhead Discovery State

## Status
Current Phase: 1
Started: {YYYY-MM-DD}
Last Updated: {YYYY-MM-DD}

## Phase Completion
- [ ] Phase 1: Problem Framing
- [ ] Phase 2: Functional Requirements
- [ ] Phase 3: Non-Functional Requirements
- [ ] Phase 4: Technology Exploration
- [ ] Phase 5: Decision Records
- [ ] Phase 6: Synthesis & Handoff

## Accumulated Context
(empty — will be populated as phases complete)

Set up progress tracking

If TodoWrite is available, create a list with one item per phase for visual progress tracking. Mark items as you progress through them.

Read the full file on GitHub · 322 lines

Files

What ships with it

2 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.

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. 2mo ago First seen · 322 lines · 14 tokens per session scan A c7631acea929

Subscribe to this mod's changes

trailhead is a skill published in the GitHub repository HartBrook/trailhead (6 stars, last pushed 8mo ago), licensed MIT. It adds 14 tokens to every session and 3,557 once invoked, about $0.0001 per session on Opus 5.5. 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

trailhead compared with skills from other repositories

trailhead next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
trailheadHartBrook/trailheadSkill68mo agoMITA14Claude Code
imagegenopenai/codexSkill135ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill316k8d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code