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.
npx agentmods add skills/peiiii/nextclaw/development-deliverynpx skills add Peiiii/nextclaw --skill development-deliverygit clone --depth 1 https://github.com/Peiiii/nextclawWrote 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.
[](https://agentmods.dev/skills/peiiii/nextclaw/development-delivery)<a href="https://agentmods.dev/skills/peiiii/nextclaw/development-delivery"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/development-delivery.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00059 | $0.01597 |
| Opus 5 | $0.00030 | $0.00798 |
| Sonnet 5 | $0.00012 | $0.00319 |
| Haiku 4.5 | $0.00006 | $0.00160 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Delivery
目标
回答“如何安全交付结果”。每个任务都交接结果;commit、push、PR、release、deploy 等外部写入仅在用户明确授权后执行。
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;
- 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。
前置合同不成立就返回正确阶段,不在 Delivery 内修代码或设计。
轻量交付
没有外部发布授权时也要完成:
- 汇报结果和主要证据;
- 披露未验证技术路径、主观确认项和残余风险;
- 判断生成物是否应保留;
- 判断 changeset、release notes 和迭代记录是否适用;
- 判断已经形成稳定证据的用户可见结果是否值得提前准备产品博客;
- 明确 commit、push、release 和 deploy 已因未授权跳过。
专项路由
每个决策只进入当前需要的一个 owner:
- 提交范围、changeset、版本笔记和用户可见更新摘要:
nextclaw-release-notes; - 重要交付、跨模块长链路、红区和发布留痕:
nextclaw-iteration-log-governance; - 有独立用户任务、可核查证据和公开叙事价值的产品成果:
nextclaw-product-blog-storytelling; - NextClaw NPM package、runtime channel、真实安装和分支闭环:
nextclaw-npm-release; - NextClaw Desktop installer、DMG、update manifest、发布和恢复:
nextclaw-desktop-release。
专项 owner 可以被本阶段路由,也可以在用户明确提出完整场景时直接触发;它们不重新编排上游开发阶段。
博客候选门
适用 Validation/Review 已形成稳定证据,且成果明显改变用户任务、有可解释 before/after、解决可复用 AI 原生问题或有真实指标/界面时,进入博客 owner;常规修复、内部重构、纯 changeset 或证据未稳定时跳过。命中不等于发布:可在任务未排除内容产物时先写内部草稿;需随版本发布则写入 changeset 绑定指令,上线、导航、配图和社交仍各自遵守授权。
发布语义
- release/deploy 使用
development-task-telemetry记录阶段、wall time、等待、重试和人工边界;workflow 输出 job/step 耗时与失败,恢复沿用 identity;最终报告实测耗时、最慢阶段和提效项。 - 每次 release/deploy 结束(含失败/取消)固定报告
AUTOMATION_INTERVENTIONS: <n>,目标为0。owning entry/prewarm至终态的 owner 外人工动作按根因计数;初始 dispatch、准备、只读观察和 owner 自动重试/恢复不计。非0时逐项报告介入点、根因和自动化消除落点;不报主观分数。 - 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。优先一次有界 wait/sleep;重复只读监控仅在净省 Token 时交给低成本 Agent,不把等待变成定时任务或高频轮询。
- 清晰自然语言与
commands/commands.md中对应的中文发布命令等价;执行前用一句话复述包含项、排除项和第一个完成点。 - “发布 NPM”只进入 NPM package owner;“发布 NextClaw 正式版”包含 NPM 与常规 runtime/product closure,但不包含 desktop;只有“桌面版”或“全平台版”才授权 desktop。
- 一键发布公开入口只收业务必要参数(全平台仅
target=all);单次 dispatch 后冻结 identity/protocol 并按 checkpoint 自动幂等恢复,禁止要求用户或 Agent 补传版本、SHA、阶段或恢复参数。 - 上下文不能确定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
- 未经用户明确要求,不 commit、push、建 PR、release、deploy 或执行不可逆操作。
- 用户要求“提交”或使用
/commit时,只在当前任务分支精确 stage/commit;用户明确说“合入主干”时,才安全集成本地master并推送origin/master。用户限制为本地时跳过 push,禁止混入无关 WIP 或把隔离分支报告为合入完成。 - 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 artifact、manifest、update channel、release notes、部署后 smoke 和分支回流。
- tag、release 页面、workflow 触发或 registry publish 只是中间状态,不自动等于交付完成。
- 任何向远程
master写入的交付或发布在远程完成门后运行pnpm release:reconcile:mainline。本地独有提交由协调器在隔离 worktree 合并、验证并普通 push;本地主 worktree 有活跃 WIP 时由单例 retry worker 自动续跑,禁止要求用户手工 pull/rebase/stash。只有脚本返回LOCAL_MAINLINE_SYNCED才报告本地同步;LOCAL_WORKTREE_RETRYING表示自动任务仍在运行,不是用户待办。 - 可恢复分叉、并行 WIP 或隔离分支只是中间状态,必须安全集成并回流主线。冲突留在恢复 worktree 继续解决和验证,不污染活跃区、不重复发布;只有真实外部依赖无法消除时报告未完成。
- 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。
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.
- 4d ago First seen · 79 lines · 59 tokens per session scan A b88c7768103d
development-delivery is a skill published in the GitHub repository Peiiii/nextclaw (253 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 1,597 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 2026-08-30.
Other skills, from other repositories
ha-skill-creator
Create, edit, improve, or audit Hope Agent skills. Use when the user wants to: (1) create a new skill from scratch, (2) edit or improve an existing skill, (3) review or clean up a SKILL.md file, (4) run evaluations to test skill effectiveness, (5) optimize skill descriptions for better trigger accuracy. Trigger…
ha-browser
Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…
ha-logs
Self-service diagnostics — query Hope Agent's local SQLite databases (logs / sessions / background jobs) directly via the exec tool to investigate problems, analyze usage, and locate root causes. Trigger on: user reports something broken / failing / slow / stuck / not responding ('X 不工作', 'X 报错', 'X 卡住', '为什么 X 失败'…
ha-pet-import
Safely import, select, switch, or enable a compatible desktop pet in Hope Agent. Resolve packages from any origin, including local folders, zip archives, pet.json plus a sprite, PNG/WebP atlases, chat attachments, repository or cloud files, direct HTTPS artifact URLs, and download pages. Use whenever a user asks to…
china-translate
中英互译 + 本地化 - 技术翻译、UI本地化、文化适配、避免机翻腔.
email-draft
Use when the user asks to draft, polish, translate, or reply to an email. Produces a clean draft with subject line, greeting, body, and sign-off, plus a pre-send self-check.