setup

An interactive command for customizing a newly initialized specd project. It studies the codebase and asks the developer to confirm project-specific build, test, and coding-convention details before writing them into the project guidance.

In plain words
What is it for?
Use it to inspect a project's source, configuration, build files, tests, and CI setup, then complete the Build & Test and Conventions sections of `AGENTS.md`.
Why use it?
It turns generic setup files into guidance that matches the actual project. Asking for confirmation helps avoid recording incorrect commands or conventions.

Command for Claude Code

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 commands/justifi-tech/web-component-library/setup
Clone the repo
git clone --depth 1 https://github.com/justifi-tech/web-component-library

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 581 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 $0.00000 $0.00581
Opus 5 $0.00000 $0.00291
Sonnet 5 $0.00000 $0.00116
Haiku 4.5 $0.00000 $0.00058

Measured yesterday against content hash f16c7e059084, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup 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 yesterday.

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.

.claude/commands/specd/setup.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are helping set up a new specd project. The framework files have already been installed via specd init. Your job is to customize them for this specific project.

Study the codebase first — read existing code, build files, configs, package manifests, Dockerfiles, Makefiles, CI configs, and anything that reveals the tech stack, conventions, and project structure.

Then work through each step interactively with the human. Ask questions, propose answers based on what you found, and get confirmation before writing.

Step 1: AGENTS.md — Build & Test

Read AGENTS.md. The Build & Test section has a placeholder comment.

Based on what you found in the codebase, propose concrete build and test commands. Examples:

  • make check, cargo test, go test ./..., npm test, pytest
  • Linters, formatters, type checkers
  • Integration test commands if they exist

Ask the human to confirm or adjust, then update the section.

Step 2: AGENTS.md — Conventions

The Conventions section has a placeholder comment.

Based on the codebase, propose language-specific conventions:

  • Language and version
  • Naming conventions (casing, prefixes)
  • Import ordering
  • Error handling patterns
  • Any patterns you see repeated in the existing code

Ask the human to confirm or adjust, then update the section.

Step 3: .claude/commands/specd/implement.md — Validation

Read .claude/commands/specd/implement.md. The validation section has a placeholder comment.

Propose concrete validation steps that match this project's tooling:

  • Test command(s) to run
  • Lint/format checks
  • Type checking
  • Any other pre-commit validation

Ask the human to confirm or adjust, then update the section.

Step 4: First spec

Ask the human what they want to build first. Help them write a spec following the format in specs/example-spec.md.

  • Start at Draft status
  • Fill in Overview, Scope, Dependencies, and as much of the Specification section as they're ready for
  • Add it to the phase table in specs/README.md

Read the full file on GitHub · 64 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. yesterday First seen · 64 lines · 0 tokens per session scan A f16c7e059084

Subscribe to this mod's changes

setup is a command published in the GitHub repository justifi-tech/web-component-library (5 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 581 tokens. 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.