pn-frontend-redo

pn-frontend-redo is a command for Claude Code, Cursor from perniemann/pnCore. It costs 69 tokens per session (1,229 once invoked), scanned A, original, MIT.

A step-by-step process for improving the user interface of an existing application through an audit, a sequence of focused changes, checks, and delivery.

In plain words
What is it for?
Use it for sequential UI work in one codebase, such as improving the home page, feature pages, and shared navigation.
Why use it?
It turns an agreed design direction into organized implementation work across several screens or interface areas.

Command for Claude CodeCursor

Written for Cursor and Claude Code: shipped in a Cursor plugin, but also a Claude Code command (commands/*.md). Also seen: mentions subagents.

Part of the pn-core plugin — 133 skills, 19 commands, 9 agents, 1 MCP server shipped together

Good fit Use it for sequential UI work in one codebase, such as improving the home page, feature pages, and shared navigation.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/perniemann/pncore/pn-frontend-redo
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.

Clone the repo
git clone --depth 1 https://github.com/perniemann/pnCore

Made for: Claude Code, Cursor.

Or install pn-core, the plugin that ships this one along with the rest of its 133 skills, 19 commands, 9 agents, 1 MCP server.

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.

agentmods badge for pn-frontend-redo

README.md
[![agentmods](https://agentmods.dev/badge/commands/perniemann/pncore/pn-frontend-redo/github.svg)](https://agentmods.dev/commands/perniemann/pncore/pn-frontend-redo)
Your own site
<a href="https://agentmods.dev/commands/perniemann/pncore/pn-frontend-redo"><img src="https://agentmods.dev/badge/commands/perniemann/pncore/pn-frontend-redo/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.

agentmods 80×15 button for pn-frontend-redo

Your own site · 80×15
<a href="https://agentmods.dev/commands/perniemann/pncore/pn-frontend-redo"><img src="https://agentmods.dev/badge/commands/perniemann/pncore/pn-frontend-redo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,229 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.01229
Opus 5 $0.00034 $0.00615
Sonnet 5 $0.00014 $0.00246
Haiku 4.5 $0.00007 $0.00123

Measured 9d ago against content hash bb33ac1b75a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pn-frontend-redo 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 9d 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.

packages/pn-core-mcp/content/commands/pn-frontend-redo.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pn-frontend-redo

Start every response with: [pn-command] 🔺

Purpose: Run a UI-only remediation program on an existing codebase: audit → plan slices → implement sequentially with artifact-backed gates → ship. Does not replace sim/backend work; scope is components, CSS, copy, and visual integration.

When to use vs similar commands

Signal Use
Existing app; UI direction locked; need execution not re-discovery Yes
Greenfield or full-stack feature No — /pn-build or /pn-design
≥2 parallel independent vertical slices (auth + payments) with contracts No — /pn-program
Single bounded tweak (one section) No — /pn-visual-tweak
Audit only, no implementation yet No — /pn-frontend-audit only (Session 1)
Scorecard exists; need roadmap only /pn-frontend-audit → plan doc; stop

Prerequisites

  • .pncore-design.md at project root (or run pn-setup design context first).
  • docs/refs/DESIGN-DOC.md or equivalent approved visual spec (optional but recommended).

Routing vs /pn-program

Pattern Command
Sequential surfaces on one repo (Home → fight pages → chrome) get_command("pn-frontend-redo")
Parallel vertical slices with worktrees + locked contracts /pn-program
One component / one page tweak /pn-visual-tweak

Session 1 — Baseline (planning only)

  1. Read .pncore-design.md and design spec.
  2. /pn-frontend-audit — scope all public routes (or plan-defined scope). Do not implement.
  3. Save baseline to docs/audits/<slug>-baseline-YYYY-MM-DD.md.
  4. pn-writing-plans — produce docs/plans/<slug>-frontend-redo-YYYY-MM-DD.md:
    • Success criteria (FR-* ids)
    • Slice table S1–Sn (routes, files, acceptance, pnCore commands)
    • Out of scope (backend, sim, etc.)
    • Program completion checklist (preflight → polish → audit → deliver)
  5. pn-create-workflow-roadmap — optional docs/WORKFLOW.md slice gate table.
  6. /pn-skeptic on the plan before Session 2.

Read the full file on GitHub · 97 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. 9d ago First seen · 97 lines · 69 tokens per session scan A bb33ac1b75a2

Subscribe to this mod's changes

pn-frontend-redo is a command published in the GitHub repository perniemann/pnCore (0 stars, last pushed 3d ago), licensed MIT. It adds 69 tokens to every session and 1,229 once invoked, about $0.0003 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 2026-08-31.

Related

Other commands, from other repositories

design-to-code

Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or a URL and produces production-ready React components, checking existing Storybook components before generating anything new. Use when implementing UI from a mockup or screenshot. To call the MCP tool…

yonatangross/orchestkit · 86 tokens

page-serve

Hand a human a rendered HTML page at a stable HTTPS URL. Registers a portless route for a file or directory (https://NAME.localhost/, never a :port), prints the URL, optionally screenshots it through agent-browser, and tears it down on stop. Use whenever an agent has produced a page a human is meant to open: glyph…

yonatangross/orchestkit · 111 tokens

t800-start

A single command for creating or updating development helpers such as rules, skills, commands, subagents, and hooks. It can target a plugin, the current project, or shared settings.

Khar-AG/t-800-agent · 0 tokens

t800-fix

A command for making a narrow, predefined fix to existing agents, skills, commands, rules, or hooks. A fix-pack is a file listing the exact changes to make.

Khar-AG/t-800-agent · 0 tokens

t-800-factory

A command that delegates creation or integration of a subagent to the T-800 Factory. It passes the proposed role, category, permissions, callers, and existing registry information to that factory.

Khar-AG/t-800-agent · 0 tokens

stripe-backend

Centralized LLM prompt instructions for Copilot and Cursor, including scripts to convert and sync rules for Python, React, Shell, and TypeScript. Designed for rapid reuse and contribution across projects.

iloveitaly/llm-ide-rules · 0 tokens