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 agentmods add commands/catlog22/claude-code-workflow/import-from-codegit clone --depth 1 https://github.com/catlog22/Claude-Code-WorkflowWhat 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 | $0.00033 | $0.06176 |
| Opus 5 | $0.00016 | $0.03088 |
| Sonnet 5 | $0.00007 | $0.01235 |
| Haiku 4.5 | $0.00003 | $0.00618 |
Grade A, and why
workflow:ui-design:import-from-code 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 541 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Design: Import from Code
Overview
Extract design system tokens from source code files (CSS/SCSS/JS/TS/HTML) using parallel agent analysis. Each agent can reference any file type for cross-source token extraction, and directly generates completeness reports with findings and gaps.
Key Characteristics:
- Executes parallel agent analysis (3 agents: Style, Animation, Layout)
- Each agent can read ALL file types (CSS/SCSS/JS/TS/HTML) for cross-reference
- Direct completeness reporting without synthesis phase
- Graceful failure handling with detailed missing content analysis
- Returns concrete analysis results with recommendations
Core Functionality
- File Discovery: Auto-discover or target specific CSS/SCSS/JS/HTML files
- Parallel Analysis: 3 agents extract tokens simultaneously with cross-file-type support
- Completeness Reporting: Each agent reports found tokens, missing content, and recommendations
- Cross-Source Extraction: Agents can reference any file type (e.g., Style agent can read JS theme configs)
Usage
Command Syntax
/workflow:ui-design:import-from-code [FLAGS]
# Flags
--design-id <id> Design run ID to import into (must exist)
--session <id> Session ID (uses latest design run in session)
--source <path> Source code directory to analyze (required)
Note: All file discovery is automatic. The command will scan the source directory and find all relevant style files (CSS, SCSS, JS, HTML) automatically.
Execution Process
Input Parsing:
├─ Parse flags: --design-id, --session, --source
└─ Decision (base path resolution):
├─ --design-id provided → Exact match by design ID
├─ --session provided → Latest design run in session
└─ Neither → ERROR: Must provide --design-id or --session
Phase 0: Setup & File Discovery
├─ Step 1: Resolve base path
├─ Step 2: Initialize directories
└─ Step 3: Discover files using script
Phase 1: Parallel Agent Analysis (3 agents)
├─ Style Agent → design-tokens.json + code_snippets
├─ Animation Agent → animation-tokens.json + code_snippets
└─ Layout Agent → layout-templates.json + code_snippets
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.
- 2d ago First seen · 541 lines · 33 tokens per session scan A e01cdd786069
workflow:ui-design:import-from-code is a command published in the GitHub repository catlog22/Claude-Code-Workflow (2,135 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 6,176 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other commands, from other repositories
ytdl
Download a video/podcast via yt-dlp, transcribe with whisper.cpp, save as markdown in llm-wiki.
verify-claim
Walk a claim through the SIFT method (Stop, Investigate, Find better coverage, Trace).
beat-brief
Draft a daily beat briefing from the files in sample-docs/.
hushflow
Configure HushFlow.
stts
User speaks the prompt, which is sent to the Model, the received response is spoken/read aloud in a loop.
cross-review
Run GitHub Copilot CLI and OpenAI Codex against the current git diff for cross-model review.