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 forge-enggit 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/forge-eng)<a href="https://agentmods.dev/skills/yike-gunshi/forge-skills/forge-eng"><img src="https://agentmods.dev/badge/skills/yike-gunshi/forge-skills/forge-eng/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/forge-eng"><img src="https://agentmods.dev/badge/skills/yike-gunshi/forge-skills/forge-eng.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 | $0.00086 | $0.03836 |
| Opus 5 | $0.00043 | $0.01918 |
| Sonnet 5 | $0.00017 | $0.00767 |
| Haiku 4.5 | $0.00009 | $0.00384 |
Grade A, and why
forge-eng 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 11d 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 — 276 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。 当前文档加载契约:先读项目CLAUDE.md、docs/README.md、docs/INDEX.md和docs/ENGINEERING.md当前真相源;PRD/DESIGN 只读相关章节,长 changelog 和 raw archive 只在追溯历史原因时加载。详见~/.claude/skills/_shared/current-doc-loading.md。
/forge-eng:工程文档管理与代码实现 v2
管理项目的 ENGINEERING.md(前后端合并),基于 PRD + DESIGN.md 产出工程方案并实现。 集成 Worktree 隔离、分级 TDD、Verification Gate。
流程总览
完整模式:
第0步 定位文档 → 第0.5步 模式选择 → 第1步 范围挑战 → 第2步 理解现状
→ 第3步 四章审查 → 第4步 方案设计 → 第5步 更新文档
→ 第5.5步 创建Worktree → 第5.6步 Dev Server 端口契约 → 第5.7步 测试框架检测
→ 第6步 任务拆分(含TDD级别) → 第7步 Wave执行(TDD+Verification)
→ 第8步 必需产出 → 第9步 确认总结 → 第10步 分支收尾
轻量模式:
第0步 定位文档 → 第0.5步 模式选择
→ 第5.5步 创建Worktree → 第5.6步 Dev Server 端口契约 → 第5.7步 测试框架检测
→ 第6步 任务拆分(含TDD级别) → 第7步 Wave执行(TDD+Verification)
→ 第9步 确认总结 → 第10步 分支收尾
全程中文。关键技术决策需用户确认后再实现。
提问格式与批量策略见 ~/.claude/skills/_shared/interaction-protocol.md。
工程原则
- 完整优先:当完整方案只比捷径多几分钟时,永远推荐完整方案(AI 辅助下"做完整"的边际成本接近零)。
- 结构与行为分离:先重构让修改变简单,再做简单的修改;不同时改结构和行为。
- 可逆性偏好:优先选择能低成本回退的实现方式(功能开关、灰度、增量替换)。
三条铁律(来自 Superpowers,不可违反)
- 不先验证就不准声称完成 — 必须运行验证命令、读取完整输出、确认 exit code 后才能 commit 或声称成功。禁用"should work"、"probably fixed"等措辞。详见 references/verification-checklist.md。
- 不先写失败测试就不准写实现(严格 TDD 级别适用)— 写了实现再补测试?删掉实现,从测试重新开始。详见 references/tdd-guide.md。
- 3 次修复失败就质疑架构 — 不要尝试第 4 次修复,停下来和用户讨论设计方案是否有根本问题。
第0步:定位项目文档
- 定位 PRD:搜索
{项目目录}/docs/PRD.md - 定位 DESIGN.md:搜索
{项目目录}/docs/DESIGN.md - 定位 RESEARCH.md:搜索
{项目目录}/docs/*RESEARCH*(如果 forge-dev 产出了调研报告) - 定位视觉决策索引(如有):优先搜索
.forge/visual-decision.md;legacy 项目才兼容旧.deliver//.do-dev/或旧docs/讨论/*/assets/*.meta.json - 定位 ENGINEERING.md:
搜索模式: - {项目目录}/docs/ENGINEERING.md - {项目目录}/docs/*engineering*(不区分大小写) - {项目目录}/docs/*工程* - {项目目录}/**/ENGINEERING*.md - 定位 ENGINEERING CHANGELOG:模式匹配
*engineering*changelog* - 分支判断:有 → 迭代模式;无 → 创建模式
What ships with it
6 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.
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.
- 11d ago First seen · 276 lines · 86 tokens per session scan A 1144151f7277
forge-eng is a skill published in the GitHub repository yike-gunshi/forge-skills (13 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 3,836 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
vastai
Vast.ai CLI to manage GPU instances, volumes, serverless endpoints, and billing.
vastai-sdk
Vast.ai Python SDK — high-level API for GPU instances, volumes, serverless endpoints, and billing.
crap-analyzer
Use to produce a risk-based refactor + test plan for recently-changed code on a diff/branch/PR by computing CRAP (complexity × untested) on changed methods. Multi-language — TypeScript, JavaScript, Python, Java, Kotlin, Go, Ruby, C#, Rust, PHP — auto-discovers how the repo generates coverage. Triggers …
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
bmad-review-edge-case-hunter
Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.
ork-review-pr
Review a pull request or branch for correctness, regressions, security, operational risk, and missing evidence. Use when a request asks to review a PR, review a diff, find real bugs, assess merge risk, or provide evidence-backed review findings. Do not use for implementation or style-only cleanup.