What is gsp-project-build?

A build workflow that turns approved interface designs into application code. It sets up foundations, creates shared components, builds screens, and checks that the project compiles at key stages.

Use it to scaffold a project, add design tokens and global styles, create reusable components, and implement designed screens.

It connects design files to an implementation process so the resulting application follows the chosen brand system and project designs.

gsp-project-build — Skill for Claude Code by jubscodes/get-shit-pretty

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 jubscodes/get-shit-pretty --skill gsp-project-build

Clone the repo

git clone --depth 1 https://github.com/jubscodes/get-shit-pretty

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jubscodes/get-shit-pretty/gsp-project-build/github.svg)](https://agentmods.dev/skills/jubscodes/get-shit-pretty/gsp-project-build)

Your own site

<a href="https://agentmods.dev/skills/jubscodes/get-shit-pretty/gsp-project-build"><img src="https://agentmods.dev/badge/skills/jubscodes/get-shit-pretty/gsp-project-build/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jubscodes/get-shit-pretty/gsp-project-build"><img src="https://agentmods.dev/badge/skills/jubscodes/get-shit-pretty/gsp-project-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,423 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.05423
Opus 5.5	$0.00000	$0.02169
Sonnet 5.5	$0.00000	$0.01085
Haiku 4.5	$0.00000	$0.00542

Measured 2mo ago against content hash aa688e8235e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gsp-project-build 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

2. If running, use `curl -s http://localhost:{port}` to fetch the page

gsp/skills/gsp-project-build/SKILL.md · 463 lines

How it starts

The opening of the file, as written. The whole thing — 463 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Works with the dual-diamond architecture: reads brand system from .design/branding/{brand}/patterns/ via brand.ref, reads/writes project assets in .design/projects/{project}/.

Pipeline architecture:

Phase 1: SCAFFOLD (skill-level, no agent)
  └─ /gsp-scaffold → verify build passes

Phase 2: FOUNDATIONS (agent: gsp-project-builder mode:foundations)
  ├─ Context: {brand-name}.yml + token-mapping.md, target-adaptations.md, STACK.md, CONVENTIONS.md
  ├─ Writes: token config, global CSS, layout, shared utils
  └─ CHECKPOINT: build must compile

Phase 3: FOUNDATION REVIEW (interactive)
  └─ Present summary → user confirms

Phase 4: COMPONENTS (agents: gsp-project-builder mode:component, parallel)
  ├─ Orchestrator: reads all design chunks → builds component manifest → partitions
  ├─ Each agent: installs/customizes/creates its assigned components
  ├─ Model assignment: round-robin (Opus/Sonnet) for rate-limit distribution
  └─ CHECKPOINT: build must compile

Phase 5: SCREENS (agents: gsp-project-builder mode:screen, parallel)
  ├─ Context per screen: its design chunk + component paths (components exist in codebase)
  ├─ Agent reads foundations + components from codebase (not from context)
  ├─ Model assignment: round-robin (Opus/Sonnet) for rate-limit distribution
  └─ CHECKPOINT: build must compile

Phase 6: EXTRACTION REVIEW (lightweight)
  └─ Grep for hardcoded values, flag remaining duplication

Phase 7: FINALIZE
  └─ BUILD-LOG, MANIFEST, STATE, phase transition

Input: Design chunks + research chunks + brief chunks + brand system chunks Output: Code in the codebase + {project}/build/BUILD-LOG.md + {project}/build/SCAFFOLD-LOG.md Agent: gsp-project-builder (spawned per phase with execution mode) Output mode: Honor ${CLAUDE_SKILL_DIR}/../../policies/output-modes.md per preferences.project_size (default compact). Build-log verbosity adapts; code output is unaffected.

<execution_context> @${CLAUDE_SKILL_DIR}/../../templates/phases/build.md </execution_context>

If .design/projects/ does not exist: output "No GSP project found. Run /gsp-start to begin." and stop.

Resolve project from .design/projects/ (one → use it, multiple → ask). Set PROJECT_PATH.

Read {PROJECT_PATH}/brand.ref → set BRAND_PATH.

Read the full file on GitHub · 463 lines

Files

What ships with it

10 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.

2mo ago First seen · 463 lines · 0 tokens per session scan A aa688e8235e2

Subscribe to this mod's changes

gsp-project-build is a skill published in the GitHub repository jubscodes/get-shit-pretty (55 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,423 tokens. 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 2026-08-30.

Claude Code ai ai-tools cli design-engineering design-systems

gsp-project-build next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gsp-project-buildjubscodes/get-shit-pretty	Skill	55	5mo ago	MIT	A	0	Claude Code
opencli-usagejackwener/OpenCLI	Skill	31k	2d ago	Apache-2.0	A	31	Claude Code
mnemonmnemon-dev/mnemon	Skill	698	7d ago	Apache-2.0	A	25	Claude Code, Codex
tokf-filtermpecan/tokf	Skill	200	yesterday	MIT	A	59	Claude Code, Codex
tokf-discovermpecan/tokf	Skill	200	yesterday	MIT	A	24	Claude Code, Codex
antv-x6-editorantvis/chart-visualization-skills	Skill	529	1mo ago	MIT	A	253	Claude Code, Codex
gpt-visantvis/chart-visualization-skills	Skill	529	1mo ago	MIT	A	63	Claude Code, Codex

gsp-project-build