feature-dev

A structured workflow for building a new software feature with discovery, design, implementation, and review. It first examines the existing project so the feature fits its current patterns and requirements.

In plain words
What is it for?
Use it when a feature needs investigation, design choices, implementation, and review in a Codex command-line workflow. It can compare possible approaches and track progress through a plan.
Why use it?
It reduces rework caused by unclear behavior, overlooked code patterns, or premature architecture choices. It keeps the work organized and asks for clarification when the request does not define important details.

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/6bnbn/flowpilot/feature-dev
Any agent
npx skills add 6BNBN/FlowPilot --skill feature-dev
Clone the repo
git clone --depth 1 https://github.com/6BNBN/FlowPilot

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 709 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 $0.00036 $0.00709
Opus 5 $0.00018 $0.00354
Sonnet 5 $0.00007 $0.00142
Haiku 4.5 $0.00004 $0.00071

Measured 2d ago against content hash 72d816c963b8, 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 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.

兼容codex@cursor一键安装技能/codex一键安装技能/.codex-home-claude-parity/skills/feature-dev/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex-Native Feature Development

Use this workflow when a feature request needs structured discovery before implementation. Keep update_plan current throughout, and use parallel explorer subagents for research only when their scopes are independent.

Source of truth

eferences/feature-dev-command.md

eferences/agent-prompts/code-architect.md

eferences/agent-prompts/code-explorer.md

eferences/agent-prompts/code-reviewer.md

Core Principles

  • Ask clarifying questions early when behavior, edge cases, or scope are underspecified.
  • Understand before acting by reading existing code patterns first.
  • Read the files surfaced by subagents instead of relying on summaries alone.
  • Prefer simple, maintainable designs over clever abstractions.
  • Use update_plan to track progress and checkpoints.

Phase 1: Discovery

Goal: Understand what needs to be built.

Actions:

  1. Create a plan that covers discovery, design, implementation, and review.
  2. If the request is underspecified, ask concrete clarifying questions.
  3. Summarize your understanding and confirm it with the user.

Phase 2: Codebase Exploration

Goal: Understand relevant code and patterns.

Actions:

  1. Spawn 2-3 explorer subagents in parallel with disjoint research scopes.
  2. Ask each subagent to return the 5-10 most important files to read next.
  3. Read the returned files yourself and consolidate the patterns you found.

Phase 3: Clarifying Questions

Goal: Resolve ambiguities before design.

Actions:

  1. Review the request and the exploration findings.
  2. Identify missing details around scope, data flow, UX, errors, compatibility, and testing.
  3. Present the open questions clearly.
  4. Wait for user answers before designing architecture.

Phase 4: Architecture Design

Goal: Compare implementation approaches with trade-offs.

Actions:

  1. If the feature is large enough to justify it, spawn 2-3 explorer or worker subagents to propose different architectural approaches.
  2. Compare the approaches by change size, maintainability, risk, and implementation speed.
  3. Recommend one approach and explain why it fits best.
  4. Ask the user to confirm the direction.

Read the full file on GitHub · 88 lines

Files

What ships with it

4 files 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. 2d ago First seen · 88 lines · 36 tokens per session scan A 72d816c963b8

Subscribe to this mod's changes

feature-dev is a skill published in the GitHub repository 6BNBN/FlowPilot (133 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 709 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 2026-08-30.

Related

Other skills, from other repositories

coding-agents-farm

To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.

griddynamics/rosetta · 32 tokens

agent-orchestration-multi-agent-optimize-v2

Multi-Agent Optimization Toolkit workflow skill. Use this skill when the user needs Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability and the operator should preserve the upstream workflow…

diegosouzapw/awesome-omni-skills · 74 tokens

nobrainer-ultra

Use when the owner says nb-ultra, nb-flow, nb-workflow, ultracode, or asks to set up, upgrade, or reconcile a project's agent workflow; or wants one non-trivial task taken from brief requirements through a complete skill-routed plan, guarded autonomous execution, useful multi-session work and final evidence audit.

nobrainer-tech/nobrainer-tech-skills · 73 tokens

nobrainer-autoimprove

Use when the owner says nb-autoimprove, deep-autoresearch, code-autoresearch, nobrainer-capture-lesson, or nobrainer-continuous-improvement; asks to improve a skill or prompt; or wants a measurable bounded baseline-variant-evaluation loop instead of one subjective rewrite.

nobrainer-tech/nobrainer-tech-skills · 70 tokens

nobrainer-dispatcher

Use when the owner says nb-dispatcher or nobrainer-dispatcher, or when an approved execution map has multiple queued work units that require ready-set selection, dependency-aware ordering, bounded parallel batches, retry scheduling, or routing audited results to the next queued unit; do not use for one coherent task…

nobrainer-tech/nobrainer-tech-skills · 89 tokens

nobrainer-review

Use when the owner says nb-review, deep-audit, deep-code-review, or deep-autoreview; explicitly requests an evidence-gated CLOSEOUT, adversarial BUGHUNT or RELEASEGATE; or needs final findings filtered to verified actionable defects. Use nobrainer-build for ordinary implementation and correction work.

nobrainer-tech/nobrainer-tech-skills · 67 tokens