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.
git clone --depth 1 https://github.com/patrickserrano/lacquerWrote 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/commands/patrickserrano/lacquer/new-feature)<a href="https://agentmods.dev/commands/patrickserrano/lacquer/new-feature"><img src="https://agentmods.dev/badge/commands/patrickserrano/lacquer/new-feature.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 | $0.00006 | $0.00447 |
| Opus 5 | $0.00003 | $0.00224 |
| Sonnet 5 | $0.00001 | $0.00089 |
| Haiku 4.5 | $0.00001 | $0.00045 |
Grade A, and why
new-feature 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 3d 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.
What it actually says
Create a new feature module following the project's architecture.
Arguments
$ARGUMENTS- Feature name in PascalCase (e.g., "Profile", "Settings")
Locate the Features Directory
Do NOT assume the app's source directory is named after the project — layouts
vary (e.g. App/, Sources/). Find the existing Features/ directory under
{{COMPONENT_PREFIX}}. (Glob for {{COMPONENT_PREFIX}}**/Features, ignoring
build output like DerivedData* and .build/) and create the module there,
as a sibling of the existing feature folders. If no Features/ directory
exists yet, create one alongside the app's other source folders under
{{COMPONENT_PREFIX}}. (the directory that holds the app's Swift sources,
next to the .xcodeproj).
Structure to Create
<features-dir>/$ARGUMENTS/
├── ${ARGUMENTS}View.swift # Main SwiftUI view
├── ${ARGUMENTS}ViewModel.swift # @Observable, @MainActor ViewModel
├── Components/ # Feature-specific UI components
└── Models/ # Feature-specific models (if needed)
Template Requirements
ViewModel
- Must use
@Observablemacro - Must be
@MainActorisolated - Must use constructor injection for dependencies
- Use
any ProtocolNamefor dependency types
View
- Use
@Statefor ViewModel - Use extracted components for complex UI
- Keep under 100 lines
Steps
- Confirm feature name with user
- Locate the
Features/directory (see above), then create the directory structure - Generate ViewModel with placeholder dependencies
- Generate main View with basic structure
- Report created files
Do NOT
- Create tests (user will request separately)
- Add to navigation (user will integrate)
- Create services/repositories (those go in Core/)
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.
- 3d ago First seen · 60 lines · 6 tokens per session scan A dbbe743183a3
new-feature is a command published in the GitHub repository patrickserrano/lacquer (3 stars, last pushed yesterday), licensed MIT. It adds 6 tokens to every session and 447 once invoked, about $0.0000 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 2026-09-03.
Other commands, from other repositories
web-vitals
Measure Core Web Vitals with a local Lighthouse run; file a task when a metric lands in the 'poor' band.
check-design
Visual design audit — quality dimensions, UI performance, production-readiness — then a task per finding.
landing-page-generator-executor.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
submit-to-directories
Submit the product to the directory catalog in /.darkflow/directories.csv through a real browser, and track what has already been submitted.
update-config
Update Dark Flow project settings: language and/or main branch.
plan-swarm
Execute a plan file with parallel agent swarm (dependency-aware).