feature-dev

A guided workflow for developing a non-trivial software feature, from understanding the request and codebase through design, implementation, review, and handoff.

In plain words
What is it for?
Use it for feature requests that need repository exploration, clarification, design decisions, implementation approval, coding, and final review.
Why use it?
It keeps feature work organized and surfaces unclear requirements and architecture choices before code is changed.

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/r13v/pi-feature-dev/feature-dev
Any agent
npx skills add r13v/pi-feature-dev --skill feature-dev
Clone the repo
git clone --depth 1 https://github.com/r13v/pi-feature-dev

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,783 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 $0.00038 $0.01783
Opus 5 $0.00019 $0.00892
Sonnet 5 $0.00008 $0.00357
Haiku 4.5 $0.00004 $0.00178

Measured yesterday against content hash 06957e5423e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-dev 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/feature-dev/SKILL.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Dev

Run a guided, tool-agnostic feature development workflow. Adapt each step to the capabilities of the current environment:

  • Track phase/progress state with any available planning mechanism, or keep a concise written checklist in chat.
  • Ask clarification and decision questions in normal chat; use structured-choice UI/tools only if available.
  • Use search, documentation, browser, or repository tools for external context when needed.
  • For broad work, optionally delegate read-only exploration, planning, or review to independent helpers if the environment supports it.

This workflow is for the main orchestrating session. Keep responsibilities clear: one writer owns file edits, while any optional helpers stay read-only unless the user explicitly approves a different handoff.

Operating Rules

  1. Clarify before coding. Do not implement until scope, acceptance criteria, constraints, and non-goals are clear enough.
  2. Explore before designing. Inspect relevant existing code and patterns before proposing architecture.
  3. Ask before implementation. Present the preferred architecture and wait for explicit user approval before editing.
  4. Keep writes single-threaded. Use the main session or one dedicated writer. Never run parallel writers in the same checkout.
  5. Review after implementation. Inspect the diff from fresh perspectives, synthesize findings, then apply only approved/worthwhile fixes.
  6. Use available tools only. If a recommended capability is unavailable, continue with the closest alternative and state the fallback briefly.
  7. For large outputs. Use any available large-output/log-processing tools. Otherwise run focused commands and summarize concise output.

Workflow

Phase 1 — Discovery

Goal: understand what needs to be built.

Actions:

  1. Establish lightweight phase tracking for Discovery, Exploration, Clarification, Architecture, Implementation, Review, and Summary/Validation. Keep exactly one phase active at a time when your environment supports explicit progress state.
  2. If the feature request is unclear, ask concise questions before doing deep work:
    • What problem should this solve?
    • What should the user-visible behavior be?
    • What constraints, deadlines, compatibility requirements, or non-goals matter?
  3. Summarize your understanding and call out assumptions.

Read the full file on GitHub · 216 lines

Files

What ships with it

1 file 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.

  1. yesterday First seen · 216 lines · 38 tokens per session scan A 06957e5423e5

Subscribe to this mod's changes

feature-dev is a skill published in the GitHub repository r13v/pi-feature-dev (2 stars, last pushed 14d ago), licensed MIT. It adds 38 tokens to every session and 1,783 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens