codex-construction

codex-construction is a skill for Claude Code, Codex from shengyy/agent-skills. It costs 56 tokens per session (3,267 once invoked), scanned B, original, MIT.

A lightweight way to divide coding work into task groups, assign each group to a coding agent, and review the results in stages. The main agent plans and checks the work while each worker handles its assigned batch.

In plain words
What is it for?
Use it to organize multi-step implementation work, run independent coding tasks concurrently, monitor workers, verify their changes, and perform a final review.
Why use it?
It gives parallel work clear boundaries and verification points, reducing conflicts and uncontrolled complexity. It also defines how to monitor progress and handle blocked tasks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads ~/.codex paths; runs codex exec; mentions Codex.

Good fit Use it to organize multi-step implementation work, run independent coding tasks concurrently, monitor workers, verify their changes, and perform a final review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shengyy/agent-skills/codex-construction
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 shengyy/agent-skills --skill codex-construction
Clone the repo
git clone --depth 1 https://github.com/shengyy/agent-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 codex-construction

README.md
[![agentmods](https://agentmods.dev/badge/skills/shengyy/agent-skills/codex-construction/github.svg)](https://agentmods.dev/skills/shengyy/agent-skills/codex-construction)
Your own site
<a href="https://agentmods.dev/skills/shengyy/agent-skills/codex-construction"><img src="https://agentmods.dev/badge/skills/shengyy/agent-skills/codex-construction/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 codex-construction

Your own site · 80×15
<a href="https://agentmods.dev/skills/shengyy/agent-skills/codex-construction"><img src="https://agentmods.dev/badge/skills/shengyy/agent-skills/codex-construction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,267 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00056 $0.03267
Opus 5.5 $0.00022 $0.01307
Sonnet 5.5 $0.00011 $0.00653
Haiku 4.5 $0.00006 $0.00327

Measured 22d ago against content hash 51e48ebd8a7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

codex-construction scanned grade B with 1 finding 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 22d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- 模型名以本机 `~/.codex/config.toml` 为准;换名先用 `codex exec -m <名字> "打印 ok"` 探针,400 即无效。
skills/codex-construction/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

codex-construction — 写好简报,然后放手

把 Codex 当成顶尖工程师:讲清为什么做、做成什么样、什么最重要、做到多好、要什么品味,然后放手。主代理也是顶尖工程师,本文只给它原则和模型推不出来的 CLI 事实。

原则

  • 硬规则只有两类:不可逆的动作边界(红线),以及启动、监控、续接依赖的 CLI 实测事实(含运行约定里的结尾标记)。这两类照做。
  • 其余都是判断:简报多长、批怎么拆、派哪一档、审几轮、何时止损,主代理定;怎么设计、实现、验证、切 commit,Codex 定。文中的具体做法都是参考。
  • 放开怎么做,写清做什么:目标、范围和完成条件越清楚,越能放手。
  • 用理由约束,不用禁令约束:担心的偏差(例如过度工程)写成「说明为什么值得」,不写成「不许」。
  • 用户的明确要求优先于本 skill。

分工

  • 主代理:吃透目标、写简报、拆批、派工、验收,把住需要用户拍板的决定。
  • Codex:一批之内的设计、实现与可逆取舍。
  • 做砸了带着反馈重派,不中途接管:接管会让验收失去独立的参照。

写简报

像给一位没参与前期讨论的顶尖同事交代任务:讲清目标和门槛,不规定做法。一份好简报覆盖下面五件事;它们是检查清单不是表格,篇幅跟着任务走,修个小 bug 几句话就够。

  1. 背景:什么项目、为什么做、做成了对谁有什么价值、走到哪一步(仓库路径、分支、前序 commit、方案文档路径)。动机讲清楚,没写的约束它能自己推出来。方案文档写目标、已和用户敲定的决定与约束,不写实现步骤,免得提前用掉 Codex 的设计空间。
  2. 交付:哪些行为可以被验证、在什么数据或场景下成立。这就是完成条件。
  3. 重点:这批真正要紧的一两件事、用户最在意什么、哪里最容易做错,以及这批不做什么。全都重要就等于没有重点。
  4. 质量与资源:门槛写成可感知的标准,例如「做到你愿意署名」;达到门槛需要的手段都授权——读任何代码、跑本地命令、重构本批涉及的代码、反复迭代。提交的测试只守真正会坏的地方,规模参照相邻测试,可逆、低影响的改动不写镜像实现的测试。知道的好工具、现成数据、同类实现和已知的坑,用「我觉得 X 够用」的口吻给,它有更好的办法就用它的。
  5. 风格与品味:像这个仓库原本就有的代码,偏好删减和简单,指一两个写得好的文件做参照。新抽象、配置项或兼容层可以引入,说清为什么值得;说不清的,通常就是过度工程。

固定结尾

  • 红线:只写不可逆的动作,用具体动作表述(push、部署、生产库、付费 API)。没有就写「无」。
  • 运行约定:施工简报照抄下面这段,把 N 换成批号。不要另外要求先交计划:单轮会话交完计划就会结束。
这是无人值守的单轮会话,没有人会回答问题,提问只会卡住整批工作。设计、实现、验证方式和可逆的取舍都由你决定,不必请示;遇到歧义,按简报和仓库代码最直接支持的理解去做,把假设写进验收包。
妨碍本批交付的问题从根因修掉。路上发现的其它问题,小而明确、不碰简报排除的部分、不影响简报要守的行为的,顺手修掉并单独 commit,方便验收时单独撤回;大的、有风险或需要取舍的,写成后续建议。交付里的每一项都实现并验证过才算完成,只交出初版、或以「下一步我会……」收尾都不算。
只有推翻简报前提、需要不可逆的决定、要越过红线,或遇到本会话排除不了的阻塞时才停下,停下前先做完不依赖它的部分。
最终消息是验收包:目标 / diff 摘要 / 删除项 / 测试状态(含预期 RED)/ 自主判断与理由 / 顺手修复 / 后续建议 / 未验证项。末尾单独一行:完成写 `STAGE N DONE <commit hash>`;需要裁决或受阻写 `BLOCKED[批N]: <原因>`。

派工前自检:没参与讨论的人只读这份简报,能不能说出为什么做、做成什么样算好、什么最重要、什么样的代码算有品味?说不出来就补简报。补不上的那段——通常是重点和品味——在用户心里,先问用户,别替用户编。

示例(中等规模的施工;运行约定省略)

背景:shop-api 的订单导出每次全量拉库,大客户导出要 10 分钟,经常超时,客服每周都在帮客户手工拆单。这批把导出改成流式分页。方案在 docs/plans/export-streaming.md,先通读;上一批已在 feat/export 分支合入游标 API(a1b2c3d)。

交付:用 scripts/seed-large.ts 生成的 50 万单数据集上,导出 1 分钟内完成、进程内存平稳;旧的全量路径删除。

重点:用户最在意的是导出不再超时。CSV 的列和格式一个字节都不能变——财务有脚本在解析它。这批不碰导入功能。

质量与资源:做到你愿意署名为止。先读懂现有的分页和鉴权代码再动手,压测不达标就继续迭代;导出模块里需要重构的就重构。测试守住游标边界、空结果和中途断连。我觉得项目里已有的 pg-cursor 够用,你有更好的办法就用你的。

风格与品味:读起来像这个仓库原本就有的代码,src/export/invoice.ts 是写得不错的同类实现。偏好删减;要加新抽象或开关,说清为什么值得。

红线:不 push、不部署、不连 .env 里的生产库。

Read the full file on GitHub · 135 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. 22d ago Changed · +25 lines · -15 tokens per session 51e48ebd8a7b
  2. 25d ago Changed 76ad6f4a7e62
  3. 1mo ago Changed · +25 lines · +5 tokens per session 06dd19da9e47
  4. 2mo ago First seen · 85 lines · 66 tokens per session scan B e6a011458293

Subscribe to this mod's changes

codex-construction is a skill published in the GitHub repository shengyy/agent-skills (2 stars, last pushed 22d ago), licensed MIT. It adds 56 tokens to every session and 3,267 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

claude-md-improver

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…

anthropics/claude-plugins-official · 82 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

gke-workload-security

Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running security audits (auditcluster.sh), enforcing Network Policies (default-deny and Dataplane V2 logging), isolating high-risk pods inside GKE Sandbox (gVisor), enforcing Pod…

google/skills · 171 tokens

gke-reliability

Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for generating K8s YAML manifests (use gke-manifest-generation) or disaster recovery…

google/skills · 85 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…

google/skills · 132 tokens

glance-canonical-layouts

Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).

android/skills · 56 tokens