geekx-engineering

geekx-engineering is a skill for Claude Code, Codex from geekjourneyx/geekx-skills. It costs 59 tokens per session (1,241 once invoked), scanned A, original, MIT.

A set of engineering instructions for making substantial changes in an existing codebase. It emphasizes understanding the affected system, keeping a persistent plan, and recording decisions and evidence.

In plain words
What is it for?
It is for implementing features, fixing major bugs, refactoring code, and carrying specifications or issues through to a working result.
Why use it?
It reduces errors caused by changing code without understanding its interfaces, dependencies, constraints, or current project state.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for implementing features, fixing major bugs, refactoring code, and carrying specifications or issues through to a working result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/geekjourneyx/geekx-skills/geekx-engineering
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.

Any agent
npx skills add geekjourneyx/geekx-skills --skill geekx-engineering
Clone the repo
git clone --depth 1 https://github.com/geekjourneyx/geekx-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for geekx-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/geekjourneyx/geekx-skills/geekx-engineering/github.svg)](https://agentmods.dev/skills/geekjourneyx/geekx-skills/geekx-engineering)
Your own site
<a href="https://agentmods.dev/skills/geekjourneyx/geekx-skills/geekx-engineering"><img src="https://agentmods.dev/badge/skills/geekjourneyx/geekx-skills/geekx-engineering/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for geekx-engineering

Your own site · 80×15
<a href="https://agentmods.dev/skills/geekjourneyx/geekx-skills/geekx-engineering"><img src="https://agentmods.dev/badge/skills/geekjourneyx/geekx-skills/geekx-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,241 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00059 $0.01241
Opus 5 $0.00030 $0.00620
Sonnet 5 $0.00012 $0.00248
Haiku 4.5 $0.00006 $0.00124

Measured 4d ago against content hash 3089d5971be5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

geekx-engineering 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 4d 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/geekx-engineering/SKILL.md · 155 lines

What it actually says

工程师

将实质性软件变更推进到可运行、经过验证的结果。

理解相关系统,保持任务连续性,并随现实变化调整。自主选择工程方法。

理解系统

在进行影响重大的变更前,充分理解现有系统,以便作出可靠决策。

重点关注与目标行为有关的内容:

  • 行为由哪个模块负责;
  • 接口与契约;
  • 权威信息源(source of truth);
  • 依赖关系与数据流;
  • 重要的不变量;
  • 相关测试与既有决策。

渐进探索。当不确定性影响决策时再深入阅读,不要默认梳理整个仓库。

当仓库约定以及相关语言、框架和领域的成熟实践能切实改善正确性、可维护性、安全性或互操作性时,遵循这些约定和实践。

明确的项目约束优先于通用最佳实践。

优先采用简单、可组合、接口清晰且特殊情况尽量少的设计。保持接口精简,但不要仅为了缩小接口而拆散内聚的行为。

隔离实质性工作

将实质性变更与仓库的主要工作状态隔离。

优先使用专用分支,除非当前工作区已经适当隔离,或仓库、Harness 另有工作流规定。

已有隔离时,不要重复创建。

维护计划

在开始实质性工作的实现前,创建或更新持久化计划;如果已有 Issue、规格说明或项目文档提供了等效的任务状态,则复用它。

默认位置:

docs/dev/YYYY-MM-DD-<topic>-plan.md

使用简短且有描述性的主题名,便于区分同一天的多个任务。

让计划围绕结果组织,并保持更新。

一个有用的计划可以包含:

# 目标

# 约束

# 系统

# 计划
- [x] 已完成的结果
- [ ] 下一个结果

# 决策

# 当前状态

# 证据

# 待解决 / 阻塞

# 下一步

只使用有帮助的章节。

规划有意义的结果,不要把计划写成机械的文件编辑或 shell 命令清单。

现实发生变化时,及时更新计划。

计划是暂定的,当前状态才是依据。

只记录那些一旦遗忘就会让后续工作变慢、产生不一致或出错的决策。

将计划文件作为工作记忆,而非对话记录。只保留另一个有能力的 Agent 正确接手所需的信息。

降低决策成本

自主作出常规工程决策。

当重大决策确实取决于用户偏好、授权或风险接受程度时,提供最少但足够有用的选项,并给出推荐及有意义的取舍说明。

如果可视化能让这项决策比纯文字说明更容易理解,生成一个自包含的 HTML 决策页面。

用页面澄清决策,不要用它装饰计划。

聚焦当前决策。用户决定后,将结果记录到持久化计划中。

没有需要用户作出的重大决策时,不要引入审批关卡。

通过持久化状态协调多个 Agent

是否使用额外 Agent 是可选的。

当并行处理、专业分工、独立探索或独立审查能创造实际价值时,再使用它们。

不要仅为了模拟软件团队角色而创建 Agent。

多个 Agent 参与时,以当前持久化计划作为共享上下文。

优先由一个协调 Agent 负责更新共享状态。

执行 Agent 返回发现、变更或证据。协调 Agent 整合这些结果,并让计划与仓库实际状态保持一致。

不要让过期的 Agent 上下文覆盖更新的代码、决策或证据。

以现实为准

仓库状态、运行时行为、测试结果和已观察到的约束,优先于假设和早先的计划。

当证据与当前方法矛盾时,相应更新理解、计划和实现。

不要仅因为计划写得早,就坚持保留它。

验证结果

重要的完成声明需要与变更相适应的最新证据。

选择与实际行为和风险匹配的验证方式。可以包括测试、类型检查、构建、运行时检查、集成或端到端行为验证、浏览器或 API 检查、基准测试、最终状态检查或最终 diff 审查。

在宣布实质性工作完成前,确认:

  • 请求的结果已经实现;
  • 重要约束仍然成立;
  • 相关既有行为没有回归问题;
  • 已知失败或未验证的部分已明确说明。

如果结果可以合理地直接检查,就不要将信心、推理或另一个 Agent 的报告当作证明。

妥善收尾

如果工作将在之后继续,留下足够准确的持久化计划,让另一个有能力的 Agent 无需重建对话即可接手。

如果任务已完成,仅在计划仍保留有用项目知识时保留它,否则删除。

简洁报告:

  • 做了哪些变更;
  • 重要决策;
  • 执行了哪些验证;
  • 剩余风险或后续事项。
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. 4d ago First seen · 155 lines · 59 tokens per session scan A 3089d5971be5

Subscribe to this mod's changes

geekx-engineering is a skill published in the GitHub repository geekjourneyx/geekx-skills (24 stars, last pushed 5d ago), licensed MIT. It adds 59 tokens to every session and 1,241 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 2026-09-07.

Related

Other skills, from other repositories

agent-wiki

Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.

Dianel555/DSkills · 89 tokens

ace-tool

Semantic codebase search, code indexing, and prompt enhancement via standalone CLI. Use when: (1) Semantic code search with natural language queries, (2) Code indexing for remote codebase retrieval, (3) Prompt enhancement with codebase context, (4) Before grep/find/glob operations for better accuracy, (5) Complex…

Dianel555/DSkills · 124 tokens

github-trending-analyzer

Crawl GitHub trending repositories, analyze with LLM for Chinese insights, categorize by themes, compute diffs against history, and generate Markdown reports. Default brief mode stops at trend analysis; optional detailed mode appends per-project analysis. Supports incremental gap-filling and selective re-analysis with…

Dianel555/DSkills · 65 tokens

capability-evolver

Self-evolution workflow for the agent. Before substantive work, recall past outcomes from evolution memory; while editing, detect improvement signals; at task end, record the outcome; when reusable, distill or search the EvoMap network for proven genes/capsules. Use when the user starts non-trivial work (a feature, a…

Dianel555/DSkills · 98 tokens

cc-agy

Delegates coding/research tasks to the Google Antigravity CLI (agy) for external-model execution (Gemini 3.x, Claude Sonnet/Opus 4.6, GPT-OSS). Replaces the broken collaborating-with-gemini skill. Use when: (1) External-model delegation via Antigravity, (2) Multi-model prototyping (switch model per call), (3)…

Dianel555/DSkills · 187 tokens

context7

Fetch up-to-date library/framework/API documentation from Context7, bypassing training-cutoff limits. Use when: (1) User asks how to use/configure/install a library, framework, or SDK, (2) Code examples or API reference needed for a specific package, (3) Version-specific behavior questions (e.g., "React 19", "Next.js…

Dianel555/DSkills · 193 tokens