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 skills add yike-gunshi/forge-skills --skill 2026-07-04-forge-deliver-retiredgit clone --depth 1 https://github.com/yike-gunshi/forge-skillsWrote 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/yike-gunshi/forge-skills/2026-07-04-forge-deliver-retired)<a href="https://agentmods.dev/skills/yike-gunshi/forge-skills/2026-07-04-forge-deliver-retired"><img src="https://agentmods.dev/badge/skills/yike-gunshi/forge-skills/2026-07-04-forge-deliver-retired/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.
<a href="https://agentmods.dev/skills/yike-gunshi/forge-skills/2026-07-04-forge-deliver-retired"><img src="https://agentmods.dev/badge/skills/yike-gunshi/forge-skills/2026-07-04-forge-deliver-retired.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00073 | $0.05589 |
| Opus 5 | $0.00036 | $0.02795 |
| Sonnet 5 | $0.00015 | $0.01118 |
| Haiku 4.5 | $0.00007 | $0.00559 |
Grade A, and why
forge-deliver scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 557 lines — stays where its author put it; the contents beside it link to each section on GitHub.
文档落地路径:遵循 forge-doc-policy 规范。完整白名单 + frontmatter schema 见
~/.claude/skills/forge-doc-policy/doc-paths.md。 当前文档加载顺序:编排层先读项目CLAUDE.md、docs/README.md、docs/INDEX.md、.features/_registry.md和相关根级当前真相源;历史账本只按需追溯。 详细规则见~/.claude/skills/_shared/current-doc-loading.md。
/forge-deliver v2:端到端交付编排层
一句话描述你的想法,拿到完整交付。
三条铁律
- 编排不实现 — deliver 不写任何业务逻辑、不做设计、不写代码。所有领域工作由对应 forge-* 子 Skill 完成。deliver 只负责:调度顺序、传递输入输出、管理状态。
- 状态必持久 — 每个 Phase 完成必须更新 state.json + 保存检查点。崩溃后
--resume能从任意 Phase 恢复。 - 证据先于断言 — 每个 Phase 完成必须有可验证的产出文件。不接受"已完成"的口头声明,必须检查文件存在且非空。
前置脚本(每次先运行)
_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
echo "当前分支: $_BRANCH"
echo "项目根目录: $_ROOT"
# 检测项目环境
[ -f "$_ROOT/package.json" ] && echo "检测到: Node.js 项目" && head -5 "$_ROOT/package.json"
[ -f "$_ROOT/requirements.txt" ] && echo "检测到: Python 项目"
[ -f "$_ROOT/go.mod" ] && echo "检测到: Go 项目"
[ -f "$_ROOT/Cargo.toml" ] && echo "检测到: Rust 项目"
[ -f "$_ROOT/Makefile" ] && echo "检测到: Makefile"
# 检查 .deliver 状态
if [ -f "$_ROOT/.deliver/state.json" ]; then
echo "====== 发现未完成的交付流水线 ======"
cat "$_ROOT/.deliver/state.json"
echo ""
echo "提示:使用 --resume 从检查点恢复"
fi
参数解析
从用户输入中解析:
| 参数 | 默认值 | 示例 |
|---|---|---|
| 模式 | 交互 | --auto(全自动) |
| 需求 | 用户输入的文字 | "给信息雷达加 RSS 订阅" |
| 恢复 | 否 | --resume(从检查点恢复) |
模式说明
交互模式(默认)
在 3 个硬卡点暂停等待用户确认:
- Phase 0 完成后 — 需求方案确认
- Phase 2 完成后 — 工程实现确认
- Phase 7 — 验收报告交付
其他 Phase 自动推进,遇到不确定问题时用 AskUserQuestion 询问。
自动模式(--auto)
前置沟通(1-2 轮,必须):
执行任何阶段之前,先完成前置沟通。这不是可选的。
第 1 轮(必选)— 需求对齐: 通过 AskUserQuestion 确认:
- "我理解你要做的是 [复述需求],对吗?"
- "项目类型判断:[frontend / backend / fullstack]"(决定是否跳过 Phase 1 的设计部分)
- "我的方案大纲是:[1-3 句话概括方案方向]"
- "预计影响 [N 个文件 / 新建 N 个文件]"
第 2 轮(按需)— 依赖确认: 只在以下情况触发:
- 检测到需要外部依赖(API key、数据库、第三方服务)
- 需求存在歧义
- 项目结构复杂(多个入口、微服务架构)
前置沟通完毕后: 全自动执行 Phase 0-7,不再暂停。
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.
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.
- 12d ago First seen · 557 lines · 73 tokens per session scan A c0962c54948d
forge-deliver is a skill published in the GitHub repository yike-gunshi/forge-skills (13 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 5,589 once invoked, about $0.0004 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
swarm-migrate
Cross-repo migration swarm — one coordinator + N parallel subagents (one per target repo) that apply the same transformation, open PRs, wait for CI, and report back to a shared JSON ledger. Coordinator handles topology, conflict auto-rebase, and stop-on-novel-failure. Use when bumping a shared dependency, rolling out…
release-management
Automates GitHub releases with semantic versioning, changelog generation from merged PRs, and gh CLI integration. Supports draft, prerelease, and standard release workflows with task-tracked multi-phase execution. Use when creating releases, tagging versions, or publishing changelogs.
release-sync
Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release digest. Optionally generates podcast from updated knowledge base. Use after tagging a new version to propagate release knowledge.
git-conventional-commits
Prepare scoped conventional commits, tags, and release messages.
ensemble-release
Automated release workflow orchestration with quality gates, smoke test integration, (Codex skill for /ensemble:release).
changelog-generator
Quick Reference - Parse conventional commits and generate categorized changelog.