code-development

A guide for developing software and changing existing code through investigation, design, implementation, review, testing, integration, and delivery.

In plain words
What is it for?
Use it for new features, bug fixes, refactoring, migrations, plugins, mods, and other code changes that need investigation and verification.
Why use it?
It helps turn a real software problem into a working result while preserving correct existing behavior.

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/pieable/dragon-ball-agent/code-development
Any agent
npx skills add pieable/dragon-ball-agent --skill code-development
Clone the repo
git clone --depth 1 https://github.com/pieable/dragon-ball-agent

Made for: Claude Code, Codex.

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,121 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 $0.00064 $0.04121
Opus 5 $0.00032 $0.02060
Sonnet 5 $0.00013 $0.00824
Haiku 4.5 $0.00006 $0.00412

Measured 2d ago against content hash be3c91c8689b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-development 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.

skills/code-development/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Development

目标是在保持用户已有工作和现有正确行为的前提下,把真实问题转化为经过设计、实现、独立评审和实际验证的可用结果。不同代码任务沿同一条主干推进:

理解问题与工程环境
→ 设计并消除关键未知
→ 小批量实现和真实集成
→ 独立评审与分层验证
→ 交付、观察和迭代

主干顺序保持稳定,执行深度随风险和未知变化。明确、低风险的局部修改可以在一次调查、修改和验证中走完。陌生平台、外部依赖、跨模块功能和难以回滚的改动需要明确完成各阶段。流程用于提高正确性,不为通过阶段制造无用文档、测试或仪式。

理解问题与工程环境

从用户要获得的结果和可观察验收路径开始,确认修改范围、必须保持的行为和当前事实。以当前代码、配置、测试和实际运行结果为准,沿最相关的入口、调用关系、数据流、依赖和已有实现建立足以支持本次决定的系统模型。区分已经证实的事实、合理推断和会改变路线的未知。

在宿主平台、框架、API 或第三方依赖上开发时,把它们视为工程环境的一部分。需要时核实当前版本的官方文档、源码、示例、发行记录和真实加载行为。不能控制的上游行为不凭记忆假定。已经能够说明代码从哪里进入、怎样与现有系统交互、结果如何观察,而且剩余未知不会改变实现路线时,停止扩展调查。

仍有会推翻总体方案的未知时,继续只读调查或做只回答该问题的最小风险实验。实验结果足以选择路线后进入设计。静态推测、mock 成功和代理指标不能代替任务要求的真实系统证据。

扩大实现、专项研究、独立评审或成套测试前,先确认本次改动经过现有系统的哪个真实入口,以及它将改变哪项用户结果。尚未确认时,继续项目调查或做只回答这个问题的最小验证。

仍有会改变 demo、工作路线或明显投入的核心价值、使用体验、成品形态或验收取舍,而且上级合同和当前项目证据都没有给出答案时,当前代码阶段不通过实现猜测用户偏好,把具体差异、已有证据和实际影响交回上级。

安全、权限和边界问题由当前代码、即将执行的具体行动或合同要求触发。没有实际触发依据的风险保留为待验证假设,不把它扩展成专项架构、研究或验证,也不用它替代对现有系统的理解。

证明路线,而不是维护路线

把用户问题、可观察结果与当前实现路线分开。框架、架构、库和工具是待验证的解决假设。除非用户或既有系统明确要求,不因已经写了代码或解决了若干路线内问题而变成必须保持的目标。新问题出现时,先判断它是目标本身需要完成的工作、可行路线内的普通缺陷、证据缺口,还是当前路线制造的结构性负担。

跨层、陌生、高成本、批量或难以回滚的路线在扩大实现前,先找出最可能否定它的用户结果,并用最小真实切片验证。最小端到端路径只证明入口和数据链能够连通,不自动证明产品方向成立。例如桌面界面的窗口启动不能代替代表性截图、交互、刷新和资源体验。语义迁移的事务成功不能代替高风险内容样本和真实检索或使用效果。样本按本任务风险选择,不把这些例子机械套到无关任务。

路线能够运行也可能已经失效。过程指标通过而代表性用户结果失败或长期未知、同一路线反复要求跨组件补偿或重建成熟平台已有能力,或者剩余工作的主体已变成维护路线自身且成本相对成熟替代明显失衡时,停止扩大投入。先做一个能区分局部缺陷与结构错配的最小实验。证据足够后按用户结果、剩余成本、风险、验证路径、可复用资产和切换代价比较继续、缩小或换路。既有投入是沉没成本,不作为继续理由,已经可靠工作的可复用部分单独保留。

路线仍有会改变方向的未知时,优先采用连续的小步试探,不把完整实现当作第一次实验。每一步应当小而真实、容易观察和尽可能可撤销,专门减少一个会改变路线的未知。开始前明确本步要回答的问题、使用的真实路径或代表性数据、支持继续与触发调整的判据,以及它与最终系统仍有什么差异。取得反馈后更新当前模型,再决定扩大、调整、补证据或换路。小步按决策信息划分,不按文件或命令机械切碎,也不要求把每次试探都变成对用户的进度汇报。路线和验收已经清楚的普通局部工作可以直接完成,不为形式增加试探。

先交付最小核心成品

对于陌生、跨层、高成本、依赖真实宿主或外部服务,或者已经出现代表性结果不推进的路线,第一次实现先交付一个最小核心成品,也就是 demo。它保留用户需求中不能缺少的核心价值,让与风险相称的代表性输入、状态或工作负载通过实际入口、核心处理、必要状态和真实依赖,产生用户可以直接判断的结果。只完成接线、框架、局部算法、测试或过程日志的技术骨架不是 demo;避开核心问题的玩具样例也不是 demo。

Demo 用于尽早判断路线是否值得扩大,不是把当前路线修到成功的义务。Demo 第一次失败后,先定位首个阻碍,并只做一个能区分局部缺陷与路线问题的最小修复或实验。这个实验没有推进核心结果或原因判断,或者同一路线为了通过 demo 不断增加前提、例外和跨组件补偿时,比较缩小、替换或重做路线,不再沿原路线补丁,也不扩展外围功能、参数组合、兼容层和成套测试。Demo 成立后,只有合同已有明确验收标准和连续推进授权时,当前代码阶段才直接扩展完整行为、边界、体验、规模和高风险验证;否则把用户可以判断的结果、差异和剩余投入交回上级校准。

Read the full file on GitHub · 111 lines

Files

What ships with it

3 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 · 111 lines · 64 tokens per session scan A be3c91c8689b

Subscribe to this mod's changes

code-development is a skill published in the GitHub repository pieable/dragon-ball-agent (10 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 4,121 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 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