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.
npx skills add sauravvarma/garage --skill spec-first-project-setupgit clone --depth 1 https://github.com/sauravvarma/garageWrote 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.
[](https://agentmods.dev/skills/sauravvarma/garage/spec-first-project-setup)<a href="https://agentmods.dev/skills/sauravvarma/garage/spec-first-project-setup"><img src="https://agentmods.dev/badge/skills/sauravvarma/garage/spec-first-project-setup.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00115 | $0.04799 |
| Opus 5 | $0.00057 | $0.02400 |
| Sonnet 5 | $0.00023 | $0.00960 |
| Haiku 4.5 | $0.00012 | $0.00480 |
Grade A, and why
spec-first-project-setup scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**When the user provides a curl:** How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec-first project setup
Bootstrap the doc structure, design directory, and Claude Code configuration that the global engineering rules depend on. Creates the skeleton — the user fills in the values.
Companion skills
This skill scaffolds the artifacts that four sibling skills depend on. The intended workflow once setup is done:
| Skill | Stage | Reads |
|---|---|---|
/design-explore |
Discover or challenge design direction | All design docs (treats them as living, can challenge) |
/design-agent |
Generate production design variants | All design docs (treats them as locked spec) |
/code-agent |
Implement features | CLAUDE.md, REPO-CONVENTIONS.md, COMPONENT-SPECS.md ([FEATURE]-IDEAS.md recommended per feature) |
/visual-qa |
Verify rendered code against spec | DESIGN-TOKENS.md, DESIGN-LANGUAGE.md, DESIGN-TAXONOMY.md |
Each companion skill runs a "spec preflight" check on first invocation and tells the user to run /spec-first-project-setup if its required artifacts are missing.
When to use
- Starting a new project from scratch.
- Adding spec structure to an existing project that has none.
- User asks to "set up docs", "scaffold specs", or "create project structure".
What it creates
docs/
├── BRIEF-AND-DIRECTION.md
├── DESIGN-LANGUAGE.md
├── DESIGN-TOKENS.md
├── COMPONENT-SPECS.md
├── DESIGN-TAXONOMY.md
├── REPO-CONVENTIONS.md # Routing, parsing, state management, analytics patterns
├── [FEATURE]-IDEAS.md # One per feature/page
└── mocks/ # API response fixtures (optional)
└── [endpoint-name].json
design/
└── .gitkeep
CLAUDE.md # Project-level Claude Code configuration
.claude/
└── rules/ # Project-specific rules (if applicable)
└── design-code-sync.md # Only for projects with design artifacts
Templates
All file templates live in assets/templates/. Each "Create" step below copies a template into place, substituting placeholders (project name, feature name, design tool, file paths). Templates use [BRACKETS] for substitutions and <!-- HTML comments --> for guidance the user fills in later.
What ships with it
11 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.
- assets/templates/brief-and-direction.md 384 B
- assets/templates/claude-md-code-only.md 759 B
- assets/templates/claude-md-design.md 1.6 KB
- assets/templates/claude-md-enterprise.md 978 B
- assets/templates/component-specs.md 396 B
- assets/templates/design-code-sync.md 2.7 KB
- assets/templates/design-language.md 980 B
- assets/templates/design-taxonomy.md 11 KB
- assets/templates/design-tokens.md 1.7 KB
- assets/templates/feature-ideas.md 4.3 KB
- assets/templates/repo-conventions.md 5.5 KB
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.
- 7d ago First seen · 246 lines · 115 tokens per session scan A 4dd00e9e4199
spec-first-project-setup is a skill published in the GitHub repository sauravvarma/garage (3 stars, last pushed 1mo ago), licensed MIT. It adds 115 tokens to every session and 4,799 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
stakeholder-brief
Write a one-page stakeholder brief translating design system health or status into business language. Trigger when someone says: stakeholder update, exec brief, leadership summary, status report for leadership, system status for non-designers, write a brief for the business, or anything about communicating design…
token-audit
Audit a design system's token definitions for naming violations, missing semantic tiers, and structural debt. This audits how tokens are defined and organised, NOT how they are consumed in code. Trigger when someone says: audit my tokens, token naming review, are my tokens consistent, token health check, review my…
figma-variable-audit
Audit Figma variable collections against token architecture best practices. Trigger when someone says: audit my Figma variables, check my Figma tokens, are my variables structured correctly, Figma variable health, review my variable collections, variable naming check, or anything about auditing the quality or…
governance-encoder
Convert governance policies into machine-executable JSON constraint files that AI agents and CI pipelines validate against automatically. This produces rule engine files in .ai/governance/, NOT narrative decision records or documentation. Trigger when someone says: encode governance rules, governance as code, automate…
cicd-integration
Generate CI/CD pipeline configurations that automate design system quality checks — token validation, component linting, visual regression, accessibility scanning, and release gating. Produces ready-to-use pipeline files for GitHub Actions, GitLab CI, CircleCI, or Bitbucket Pipelines, configured to enforce the…