Agent skill

Architect Before You Build

by jsmastery-pro in jsmastery-pro/jsm-agent-skill

Runs a short design conversation before coding: aligns on terms, works through the decisions that matter and ends with a plan you confirm.

MITAuto-check passedAgent Workflows

Install Architect Before You Build

skills CLI
$ npx skills add jsmastery-pro/jsm-agent-skill --skill architect -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jsmastery-pro/jsm-agent-skill architect --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jsmastery-pro/jsm-agent-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/architect .claude/skills/architect && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
architect
GitHub stars
216
Token cost
~1.1k tokens
SKILL.md length
540 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Runs a short design conversation before coding: aligns on terms, works through the decisions that matter and ends with a plan you confirm.

  • Works in 5 steps: Understand What's Here → Align on Language → Think Through the Decisions Together → …
  • Before starting a new feature that has unclear scope
  • SKILL.md covers Step 1 — Understand What's Here, Step 2 — Align on Language, Step 3 — Think Through the… and Step 4 — Know When You Are Done, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Think of this as a design conversation held before coding starts, with the agent playing a senior engineer who does the homework first. It reads the feature description, any context files and existing code, and does not ask about anything the documentation already answers.

Next it aligns vocabulary: it picks three to five terms in the feature description that could mean different things, proposes a definition for each from context and waits for your confirmation or correction before moving on. Then it works through only the decisions that would change what gets built, one question at a time, in order of impact, saying what it would do and why so you have something to react to.

The aim is a thinking session, not an interrogation, and the description says it ends with a clear implementation plan that you confirm before anything starts. The final step, on knowing when the discussion is done, is cut off in the supplied text.

When your agent uses it

  • Before starting a new feature that has unclear scope
  • Settling the key technical decisions with an agent before it writes code
  • Making sure you and the agent mean the same thing by project terms

Example prompts

  • “Before we build the notifications feature, think it through with me like a senior engineer.”
  • “Help me work out the decisions behind a multi-tenant billing page, then give me a plan to confirm.”
  • “I want to add CSV import. Align on terms first, then ask only what matters.”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Understand What's Here
  2. Align on Language
  3. Think Through the Decisions Together
  4. Know When You Are Done
  5. Produce the Implementation Plan

What it can do on your machine

Read from SKILL.md and the folder at commit fd85d6a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Architect Before You Build loads about 1.1k tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 540 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jsmastery-pro/jsm-agent-skill at commit fd85d6a, republished under its MIT licence (© jsmastery-pro). 540 words, ~1,142 tokens.

Download SKILL.mdSave it as .claude/skills/architect/SKILL.md (or your agent's skills folder).
name
architect
description
Think through what you are about to build like a senior engineer before writing any code. Surfaces decisions, aligns on language, and produces a clear implementation plan you confirm before anything starts.

You are a senior engineer sitting with a developer before they start building. Your job is not to interrogate them — it is to think alongside them. To ask the questions a senior engineer would ask before letting someone start coding. To catch the things that seem obvious but aren't. To make sure both of you are building the same thing in your heads before either of you touches the code.

This is a thinking session. Not a grilling session.

Step 1 — Understand What's Here

Before saying anything, take stock of what already exists:

  • Read the feature description the developer gave you
  • Read any context files, documentation, or existing code available
  • Build a clear picture of what needs to be built and what already exists

Do not ask about anything already clearly answered by existing documentation. A good senior engineer does their homework before the meeting.

Step 2 — Align on Language

Every project has its own vocabulary. Before discussing implementation, make sure you and the developer mean the same thing by the same words.

Identify 3-5 terms from the feature description that could be interpreted more than one way. Define each one based on what you understand from the context. Present them to the developer for confirmation.

Before we think this through — let me make sure
we are speaking the same language:

- "[Term]" — I understand this to mean [definition].
  Is that right?
- "[Term]" — I am treating this as [definition].
  Does that match what you have in mind?

Correct anything that is off before we go further.

Update your understanding immediately if the developer corrects a term. Do not continue until the language is aligned.

Step 3 — Think Through the Decisions Together

Now surface the decisions that would meaningfully change what gets built. Not every possible question — only the ones where the answer changes the implementation direction.

A senior engineer knows the difference between a decision that matters and a detail that can be figured out during coding. Ask only what matters.

For each decision:

  • Ask one question at a time
  • Share what you would do and why — give the developer something to react to, not a blank page to fill
  • Listen to their answer before moving to the next decision
  • If their answer makes another decision irrelevant — skip it
[The decision that needs to be made]

My thinking: [what you would do and the reason behind it]

What do you think — does that approach work for you,
or do you see it differently?

Work through decisions in order of impact. The decision that affects the most downstream work comes first.

Show full SKILL.md (194 more words)Show less

Step 4 — Know When You Are Done

Stop when every decision that would change the implementation has been resolved. Not when every possible question is answered. When what matters is settled.

A good senior engineer knows when the plan is solid enough to start. They do not keep asking questions for the sake of being thorough.

When you are done, say:

Blueprint ready.

Step 5 — Produce the Implementation Plan

After saying "Blueprint ready", write a clear implementation plan based on everything discussed.

## Implementation Plan — [Feature Name]

### What we are building
[One clear paragraph describing exactly what will be built]

### Language we agreed on
- [Term]: [agreed definition]
- [Term]: [agreed definition]

### Decisions made
- [Decision]: [what was decided and the reasoning]
- [Decision]: [what was decided and the reasoning]

### Assumptions
- [Anything you assumed that was not explicitly confirmed]

### How to build it
[A concise ordered list of implementation steps]

Present the plan to the developer. Wait for them to confirm before anything gets built.

Only after explicit confirmation does implementation begin.

What This Session Is Not

This is not an interrogation. You are not trying to catch the developer out or prove their plan is wrong. You are helping them think more clearly before they build.

This is not a specification session. You are not writing a full spec document. You are aligning on the decisions that matter so the implementation can start with confidence.

This is not open-ended. You are not asking questions forever. You are asking what matters, confirming the plan, and getting out of the way so building can begin.

© jsmastery-pro, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/architect of jsmastery-pro/jsm-agent-skill.

Open the folder on GitHubat commit fd85d6a

Compare with similar skills

Architect Before You Build next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Architect Before You Build compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Architect Before You Build this skilljsmastery-pro/jsm-agent-skill216—~1.1kAutomated safety check: PassMIT
Brainstorming Before BuildingjnMetaCode/superpowers-zh8.3k—~1.8kAutomated safety check: PassMIT
CE BrainstormEveryInc/compound-engineering-plugin25k—~1.9kAutomated safety check: PassMIT
Feature BrainstormVeryGoodOpenSource/vgv-wingspan108—~1.8kAutomated safety check: PassMIT
Explorexwtro0tk1t-cloud/harness265—~1.6kAutomated safety check: PassNone
Iterative Development Orchestratorprime-radiant-inc/iterative-development181—~2.7kAutomated safety check: PassApache-2.0

Similar skills

  • Brainstorming Before Building

    jnMetaCode/superpowers-zh

    Turns a rough idea into an approved design before any code is written, sorting the request into spike, bounded or architectural and enforcing an approval gate.

    8.3k GitHub stars~1.8k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed
  • CE Brainstorm

    EveryInc/compound-engineering-plugin

    Turns a vague or ambitious feature idea into a requirements-only plan through dialogue with you, sized to the work, before any code is written.

    25k GitHub stars~1.9k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Feature Brainstorm

    VeryGoodOpenSource/vgv-wingspan

    Clarifies what to build before how, by asking one question at a time about a feature idea and then handing the result on to planning.

    108 GitHub stars~1.8k tokensUpdated 7 days ago
    Agent WorkflowsAuto-check passed
  • Explore

    xwtro0tk1t-cloud/harness

    Graph-driven project understanding using code-review-graph (CRG).

    265 GitHub stars~1.6k tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed
  • Iterative Development Orchestrator

    prime-radiant-inc/iterative-development

    Runs an autonomous loop that extracts requirements with proof obligations, builds a walking skeleton, then audits sprint by sprint against real behavior evidence.

    181 GitHub stars~2.7k tokensUpdated 4 mo ago
    Agent WorkflowsAuto-check passed
  • Spec-Driven Development

    LichAmnesia/lich-skills

    Runs a gated Spec, Plan, Build, Test, Review, Ship workflow so non-trivial changes are specified, verified and reviewed before they ship, with a named artifact per phase.

    234 GitHub stars~3.5k tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed

More from jsmastery-pro/jsm-agent-skill

  • Imprint UI Consistency Registry

    jsmastery-pro/jsm-agent-skill

    Run after building a UI component to record its background, border, radius and text classes in ui-registry.md so later components match what came before.

    216 GitHub stars~2.3k tokensUpdated 3 mo ago
    Auto-check passed
  • Build Failure Recovery

    jsmastery-pro/jsm-agent-skill

    Diagnoses which of three failure modes a stalled AI-assisted build is in, then chooses a targeted fix, a hard reset or a rethink instead of more prompting.

    216 GitHub stars~1.8k tokensUpdated 3 mo ago
    Auto-check passed
  • Session Save and Restore

    jsmastery-pro/jsm-agent-skill

    Saves the essential state of a coding session to memory.md at the end, restores it at the start of the next one, and keeps secrets out of the saved notes.

    216 GitHub stars~1.9k tokensUpdated 3 mo ago
    Auto-check passed
  • Post-Feature Review

    jsmastery-pro/jsm-agent-skill

    Compares a finished feature with its plan, the project's architecture and design rules, and production-readiness checks, then reports issues without fixing them.

    216 GitHub stars~1.3k tokensUpdated 3 mo ago
    Auto-check passed

Questions about Architect Before You Build

What does Architect Before You Build do?

Runs a short design conversation before coding: aligns on terms, works through the decisions that matter and ends with a plan you confirm. Think of this as a design conversation held before coding starts, with the agent playing a senior engineer who does the homework first. It reads the feature description, any context files and existing code, and does not ask about anything the documentation already answers.

When should I use Architect Before You Build?

Architect Before You Build fits situations like: before starting a new feature that has unclear scope; settling the key technical decisions with an agent before it writes code; making sure you and the agent mean the same thing by project terms.

How do I install Architect Before You Build in Claude Code?

Run `npx skills add jsmastery-pro/jsm-agent-skill --skill architect -a claude-code`. Or copy the skill folder (skills/architect in jsmastery-pro/jsm-agent-skill) into .claude/skills/architect in your project. Claude Code loads it when a task matches its description.

How do I install Architect Before You Build in Codex?

Run `npx skills add jsmastery-pro/jsm-agent-skill --skill architect -a codex`. Or copy the skill folder (skills/architect in jsmastery-pro/jsm-agent-skill) into .agents/skills/architect in your project. Codex loads it when a task matches its description.

Can I use Architect Before You Build in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jsmastery-pro/jsm-agent-skill --skill architect -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/architect, .gemini/skills/architect, .github/skills/architect and .opencode/skills/architect in your project.

What does Architect Before You Build need to run?

SKILL.md names no scripts, command-line tools or credentials: Architect Before You Build is instructions for the agent only.

Does Architect Before You Build access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Architect Before You Build safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Architect Before You Build use?

Architect Before You Build is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Architect Before You Build use?

About 1.1k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Architect Before You Build?

Skills that share tags, products or a category with Architect Before You Build: Brainstorming Before Building (jnMetaCode/superpowers-zh, 8.3k stars), CE Brainstorm (EveryInc/compound-engineering-plugin, 25k stars), Feature Brainstorm (VeryGoodOpenSource/vgv-wingspan, 108 stars) and Explore (xwtro0tk1t-cloud/harness, 265 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Architect Before You Build?

jsmastery-pro (a GitHub organization) maintains it in jsmastery-pro/jsm-agent-skill, which has 216 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on July 9, 2026.

Source: jsmastery-pro/jsm-agent-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.