complex-feature-dev

A seven-phase workflow for developing complex software features, from discovery and design through implementation, review, and summary. It keeps durable plans and findings in files such as task_plan.md and progress.md.

In plain words
What is it for?
Use it to explore an unfamiliar codebase, clarify feature requirements, choose an architecture, implement the feature, review it, and record the result.
Why use it?
It provides a shared record of decisions and unfinished work during long feature tasks. It also requires unclear requirements to be resolved before implementation begins.

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/littlestudent886/complex-dev-skills/complex-feature-dev
Any agent
npx skills add littlestudent886/complex-dev-skills --skill complex-feature-dev
Clone the repo
git clone --depth 1 https://github.com/littlestudent886/complex-dev-skills

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,792 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 $0.00032 $0.02792
Opus 5 $0.00016 $0.01396
Sonnet 5 $0.00006 $0.00558
Haiku 4.5 $0.00003 $0.00279

Measured 2d ago against content hash 35c6db179e90, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

complex-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 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.

claude/plugins/complex-feature-dev/skills/complex-feature-dev/SKILL.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Development (Complex Tasks)

A codebase-agnostic workflow for building new features safely:

  • 7 phases (discovery → exploration → questions → architecture → implement → review → summary)
  • Persistent planning files for long tasks (macro memory: goal, status, next actions, and durable decisions)

Inputs

Minimum input:

  • A 1–2 sentence feature description (what to build + who/why).

Helpful extras (optional):

  • Acceptance criteria / examples
  • Related files or modules
  • Docs / tickets / prototypes (if inaccessible, ask user to paste key parts)

Non-Negotiable Rules

  1. Never skip Phase 3 (Clarifying Questions). If anything is underspecified, ask and wait.
  2. Never start Phase 5 (Implementation) without explicit approval.
  3. Use the planning files as persistent macro memory. Keep them concise and durable.
  4. Read before decide. Before major decisions, re-read task_plan.md.
  5. Log errors briefly + don’t repeat failures. If an action fails, change the approach.

Quick Start (Planning Files)

This workflow requires these files in the repo root:

  • task_plan.md
  • findings.md
  • progress.md
  • CLAUDE.md (agent instructions; created by init if missing)

To initialize them, run:

  • /complex-feature-dev:init (recommended)

Or via terminal:

  • macOS/Linux (or Windows Git Bash): bash "$(ls -dt ~/.claude/plugins/cache/complex-dev-skills/complex-feature-dev/*/scripts/init-session.sh 2>/dev/null | head -1)"
  • Windows PowerShell: pwsh -ExecutionPolicy Bypass -File "~/.claude/plugins/cache/complex-dev-skills/complex-feature-dev/<version>/scripts/init-session.ps1"

Project Guidelines

  • Follow AGENTS.md / CLAUDE.md / CONTRIBUTING.md / README.md if present.
  • Prefer matching existing code patterns over introducing new abstractions.
  • Write important conventions you discover into findings.md.

Phase 1: Discovery

Goal: Make the request concrete and testable.

  • If planning files are missing, run the initializer script via the Bash tool and do not proceed until the files exist.
  • Restate the request as acceptance criteria; confirm scope and non-goals.
  • Capture constraints (compatibility, performance, time, rollout).
  • Write brief confirmed requirements + acceptance criteria to findings.md.

Read the full file on GitHub · 302 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. 2d ago First seen · 302 lines · 32 tokens per session scan A 35c6db179e90

Subscribe to this mod's changes

complex-feature-dev is a skill published in the GitHub repository littlestudent886/complex-dev-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 32 tokens to every session and 2,792 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.