code-pilot

A development workflow that first clarifies a task, then chooses a process for frontend or other software work. Frontend work may include a visual sketch and design review before implementation and verification.

In plain words
What is it for?
Planning and carrying out frontend changes, backend or other coding tasks, and final verification. It can guide when to use visual design steps, written plans, or separate coding agents.
Why use it?
It helps structure development work so requirements, design, implementation, and checks are handled in an expected order. It also provides a defined route for tasks that do not involve a user interface.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/ysicing/code-pilot/code-pilot
Any agent
npx skills add ysicing/code-pilot --skill code-pilot
Clone the repo
git clone --depth 1 https://github.com/ysicing/code-pilot

Made for: Claude Code, Codex.

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,893 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00068 $0.01893
Opus 5 $0.00034 $0.00946
Sonnet 5 $0.00014 $0.00379
Haiku 4.5 $0.00007 $0.00189

Measured yesterday against content hash 02b387096a80, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-pilot 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 yesterday.

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.

skills/code-pilot/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Pilot

Universal development workflow. Routes frontend tasks through design-first process; all other tasks go directly to superpowers standard workflow.

Route Decision

digraph code_pilot {
    "superpowers:brainstorming\n(clarify requirements)" [shape=box];
    "Has frontend / UI?" [shape=diamond];

    "Offer Visual Companion\n(standalone message only)" [shape=box];
    "User accepts?" [shape=diamond];
    "Read visual-companion.md\nthen sketch in browser" [shape=box];
    "User approves sketch?" [shape=diamond];
    "Revise sketch" [shape=box];
    "Run ui-ux-pro-max\n--design-system" [shape=box];
    "Confirm design direction" [shape=box];

    "superpowers:writing-plans" [shape=box];
    "Choose execution mode" [shape=diamond];
    "superpowers:subagent-driven-development" [shape=box];
    "superpowers:executing-plans" [shape=box];
    "superpowers:verification-before-completion" [shape=doublecircle];

    "superpowers:brainstorming\n(clarify requirements)" -> "Has frontend / UI?";

    "Has frontend / UI?" -> "Offer Visual Companion\n(standalone message only)" [label="yes"];
    "Has frontend / UI?" -> "superpowers:writing-plans" [label="no"];

    "Offer Visual Companion\n(standalone message only)" -> "User accepts?";
    "User accepts?" -> "Read visual-companion.md\nthen sketch in browser" [label="yes"];
    "User accepts?" -> "Run ui-ux-pro-max\n--design-system" [label="no"];
    "Read visual-companion.md\nthen sketch in browser" -> "User approves sketch?";
    "User approves sketch?" -> "Revise sketch" [label="no"];
    "Revise sketch" -> "User approves sketch?";
    "User approves sketch?" -> "Run ui-ux-pro-max\n--design-system" [label="yes"];
    "Run ui-ux-pro-max\n--design-system" -> "Confirm design direction";
    "Confirm design direction" -> "superpowers:writing-plans";

    "superpowers:writing-plans" -> "Choose execution mode" [label="plan written"];
    "Choose execution mode" [shape=diamond];
    "Choose execution mode" -> "superpowers:subagent-driven-development" [label="recommended"];
    "Choose execution mode" -> "superpowers:executing-plans" [label="inline"];
    "superpowers:subagent-driven-development" -> "superpowers:verification-before-completion";
    "superpowers:executing-plans" -> "superpowers:verification-before-completion";
}

Read the full file on GitHub · 163 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. yesterday First seen · 163 lines · 68 tokens per session scan A 02b387096a80

Subscribe to this mod's changes

code-pilot is a skill published in the GitHub repository ysicing/code-pilot (38 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,893 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 2026-08-30.