nextclaw: Skill for Claude Code

.agents/skills/development-delivery/SKILL.md

development-delivery is a skill for Claude Code, Codex from Peiiii/nextclaw. It costs 59 tokens per session (1,132 once invoked), scanned A, original, MIT.

A workflow guide for handing finished software to users through commits, releases, or deployments. A deployment puts software into its target environment, while a release makes a version available to others.

In plain words
What is it for?
Use it to prepare delivery summaries, release notes, changesets, iteration records, package releases, desktop installers, or deployments. It also records skipped actions and remaining risks when publishing is not authorized.
Why use it?
It checks that the work is verified, reviewed, within scope, and safe to hand over before any external change is made. It also makes clear which publishing actions need the user's permission.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Peiiii/nextclaw's own configuration. It tells Claude Code and Codex how to work on nextclaw itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nextclaw configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Peiiii/nextclaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Peiiii/nextclaw/master/.agents/skills/development-delivery/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Peiiii/nextclaw

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 development-delivery

README.md
[![agentmods](https://agentmods.dev/badge/skills/peiiii/nextclaw/development-delivery/github.svg)](https://agentmods.dev/skills/peiiii/nextclaw/development-delivery)
Your own site
<a href="https://agentmods.dev/skills/peiiii/nextclaw/development-delivery"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/development-delivery/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 development-delivery

Your own site · 80×15
<a href="https://agentmods.dev/skills/peiiii/nextclaw/development-delivery"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/development-delivery.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 1,132 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.01132
Opus 5.5 $0.00024 $0.00453
Sonnet 5.5 $0.00012 $0.00226
Haiku 4.5 $0.00006 $0.00113

Measured 1mo ago against content hash 1b4a211898b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

development-delivery 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 1mo 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.

.agents/skills/development-delivery/SKILL.md · 65 lines

What it actually says

Development Delivery

目标

每个任务都交接结果;commit、push、PR、release、deploy 和不可逆操作须用户明确授权,或有当前项目可核对的既有明确授权。

进入门

进入时确认:

  • 可观察目标和交付范围;
  • 适用验证已经通过且证据未因后续修改失效;
  • 适用 Review 已无未关闭 findings;
  • 工作区中的用户或其它任务改动已经隔离;曾切换 worktree 时,已取得草稿迁移及源区查漏证据,规则、文档和复盘也已纳入本次交付范围;
  • 外部动作的对象、范围和授权明确。
  • active contract 存在时,本次交付对应 stable acceptance IDs 已明确且证据当前有效。

前置条件不成立则返工,不在 Delivery 修代码或设计。

轻量交付

用户可操作的产品变化默认执行用户验收交付,不等用户索要链接;取得当前范围有效 AI 验收结论后,按该合同交齐入口、操作与预期、验证边界和状态。未发布不是省略验收入口的理由。

没有外部发布授权时也要完成:

  • 汇报结果、证据、未验证链路、主观确认项和残余风险;
  • 判断生成物保留及项目已有的变更说明、版本记录和迭代记录是否适用;
  • 判断已形成稳定证据的用户可见结果是否需要项目内容材料;
  • 明确 commit、push、release 和 deploy 已因未授权跳过。

专项路由

提交范围、版本说明、产品发布、文档部署和 Git 主线协调以当前项目的明确合同为准。每个决策只读取当前需要的一个项目专项方法;项目没有发布合同,不把“提交成功”或“产物构建成功”称为完整发布。维护发布机制或修复发布失败时读取版本演进门。专项 owner 只完成自己的发布或交付子目标,不重新编排上游开发阶段。

博客候选门

项目有内容发布 owner,且适用 Validation/Review 已形成稳定证据时,按项目合同判断是否准备内容材料;内容发布仍遵守独立授权。

发布语义

  • 发布前明确对象、版本、环境、授权范围和可观察完成点;自然语言宏只按项目权威登记解释。
  • 外部等待只在完成点、风险、失败或需决策时更新;状态未变不发心跳。重试遵守 owning workflow 的幂等与恢复合同。
  • 一次发布按项目合同核对产物、部署、可用性和回滚或恢复;已成功的不可逆步骤不重复执行。
  • 上下文不能确定发布对象时只问一个短问题;存在“只、仅、不包含”等限制词时以更窄授权为准。

外部动作

  • 用户只要求“提交”时,只在当前任务分支精确 stage/commit;是否合并、推送及目标分支按用户授权和项目 Git 合同判断。禁止混入无关 WIP 或把隔离分支报告为主线完成。
  • 发布使用仓库既有 release flow,不以零散原子命令伪装完整闭环。
  • 发布完成必须覆盖授权范围内适用的产物、说明、部署后验证和分支状态。
  • 可恢复分叉、并行 WIP 或隔离分支只是中间状态;合入主线的任务按项目合同安全集成,不污染活跃区或要求用户手工处理本可由系统恢复的步骤。
  • 部分发布或外部失败优先进入专项恢复分支;不得重复发布已经成功的不可逆步骤。
  • active contract 下只返回 acceptance_updates 与 parent_status;artifact、版本或 release 不能完成 parent-goal,交回 lifecycle 执行 completion gate。

输出

报告范围、证据、授权与执行结果、缺口、恢复入口及残余 WIP;验收交付一次给齐入口、步骤和预期。有 active contract 时报告 stable ID 更新并返回 parent;不得把部分完成表述成全部完成。完整开发或授权发布的 Delivery 完成时,返回 parent_status=ready-for-retrospective 与交付证据,由 Lifecycle 路由复盘后再做整体完成判断;仅授权发布而直接进入 Delivery 的任务也要完成这一交接。外部发布成功、长时间等待结束或用户催促均不跳过;纯调查、设计或 Review 的限定单阶段产物不因此扩大范围。

本阶段不修改产品实现、不关闭 Review findings,也不把内部工程记录直接拼成用户 release notes。

Files

What ships with it

2 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. 1mo ago Changed 1b4a211898b4
  2. 1mo ago Changed · -14 lines c64210b0c341
  3. 1mo ago Changed dbde53a47e4e
  4. 1mo ago Changed 282cb2467007
  5. 1mo ago Changed · +1 lines ca8ea61bb76f
  6. 1mo ago Changed e3f6905fdf3e
  7. 1mo ago Changed · -1 lines 920c6ae10a34
  8. 2mo ago Changed cac55732636d
  9. 2mo ago First seen · 79 lines · 59 tokens per session scan A b88c7768103d

Subscribe to this mod's changes

development-delivery is a skill published in the GitHub repository Peiiii/nextclaw (263 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 1,132 once invoked, about $0.0002 per session on Opus 5.5. 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

development-delivery compared with skills from other repositories

development-delivery next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
development-deliveryPeiiii/nextclawSkill263yesterdayMITA59Claude Code, Codex
publish-siteandrooAGI/starnetSkill1.7k6d agoMITA50Claude Code, Codex
graincrawlvincentkoc/dotskillsSkill111yesterdayMITA47Codex
crawlkitvincentkoc/dotskillsSkill111yesterdayMITA30Codex
aetox-deployMikedev115/AetoxSkill4829d agononeA102Claude Code, Codex
land-and-deploygarrytan/gstackSkill140kyesterdayMITA14Claude Code
release-publishrohitg00/ai-engineering-from-scratchSkill77kyesterdayMITA9Claude Code, Codex