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-statusgit 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-status)<a href="https://agentmods.dev/skills/yike-gunshi/forge-skills/forge-status"><img src="https://agentmods.dev/badge/skills/yike-gunshi/forge-skills/forge-status/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-status"><img src="https://agentmods.dev/badge/skills/yike-gunshi/forge-skills/forge-status.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 | $0.00103 | $0.02497 |
| Opus 5 | $0.00051 | $0.01248 |
| Sonnet 5 | $0.00021 | $0.00499 |
| Haiku 4.5 | $0.00010 | $0.00250 |
Grade A, and why
forge-status 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 — 217 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。
/forge-status:并行会话巡检 + 清理
设计哲学
只读扫描 + 一次确认 + 硬信号判定。
- 多会话并行的心跳文件是
.forge/active.md,当前由 forge-bugfix 在领取任务时追加(P2/P3 之后登记)、由 forge-fupan 在会话结束时清理 - 但人会漏复盘、会话会崩掉、worktree 可能被手动删,导致 active.md 里残留"僵尸"记录
- 本 skill 专治僵尸:扫一遍表 → 按硬信号判活/死 → 让你确认后清理
硬信号(僵尸判定):
- 对应 worktree 目录不存在 → 真·已弃用或已清理
- 对应分支已
merged到 main/master → 真·已完成,只是漏清理 - 以上两个都不满足 → 真·活跃,保留
明确不用的信号:
- ❌ 时间戳 / "超过 N 小时" / "启动超过 N 天"——这些不代表工作完成
- ❌ 最近 commit 时间——AI 慢不等于僵尸
- ❌ 进程存活检查——Claude Code 会话结束后进程就没了,不代表工作废弃
Dev server 附加巡检(不参与僵尸判定):
- 可以报告
.devserver.json、tmux session、监听端口、PID、cwd,帮助用户发现多余前后端 - 这些信息只用于"有哪些服务在跑"的可见性,不用于判定
.forge/active.md的会话是否僵尸 - 如需停止服务,优先提示用户在对应 worktree 内运行项目自己的
npm run dev:stop/scripts/dev-stack.sh stop
两种调用模式
| 模式 | 调用方 | 行为 |
|---|---|---|
| 交互清理(默认) | 用户说 /forge-status / "看下 forge 状态" / "清理 worktree" |
扫 → 报告 → 问 y/n → 清理 |
| 只读巡检 | forge-bugfix 的 P0 阶段自动调用 | 扫 → 只报告"当前有 N 个活跃会话,其中 M 个疑似僵尸",不清理 |
调用方通过自然语言区分:
- 用户直接触发 → 走交互清理
- 其他 skill 委托 → 在调用文本中说"只读巡检,不要清理"
流程
步骤 0:前置定位
_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
ACTIVE="$_ROOT/.forge/active.md"
if [ ! -f "$ACTIVE" ]; then
echo "(本项目暂无 .forge/active.md,说明还没用过并行化流程)"
exit 0
fi
步骤 1:解析 active.md
读 .forge/active.md 的"进行中会话"节,按行解析字段:
- session: <id> / worktree: <path> / 任务: <id> / 域: <domains>
跳过注释行(<!--、-->)和空行。
步骤 2:逐条硬信号判定
对每条记录:
# 1) worktree 是否存在
if [ ! -d "$WT_PATH" ]; then
verdict="已删除" # 可清理
reason="worktree 目录不存在"
continue
fi
# 2) 分支是否已合并到 main(或 master)
_MAIN_BRANCH=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|^refs/remotes/origin/||' || echo "main")
_WT_BRANCH=$(git -C "$WT_PATH" branch --show-current 2>/dev/null)
if git branch --merged "$_MAIN_BRANCH" 2>/dev/null | grep -qE "^\s*${_WT_BRANCH}$"; then
verdict="已合并" # 可清理
reason="分支 ${_WT_BRANCH} 已合并到 ${_MAIN_BRANCH}"
continue
fi
# 3) 两个都不满足 → 活跃
verdict="活跃"
reason="worktree 存在 + 分支未合并"
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 · 217 lines · 103 tokens per session scan A da5bfa0420be
forge-status is a skill published in the GitHub repository yike-gunshi/forge-skills (13 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 2,497 once invoked, about $0.0005 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…
vastai
Vast.ai CLI to manage GPU instances, volumes, serverless endpoints, and billing.
dev
One-command dev loop boot. Spins up portless (named HTTPS subdomain), emulate (stateful API mocks), the project's dev server, and an agent-browser session, all keyed to the current git branch. Use when starting a feature branch, switching worktrees, or returning to a project after a break. Skips silently with install…
github-operations
GitHub CLI operations for issues, PRs, milestones, and Projects v2. Covers gh commands, REST API patterns, and automation scripts. Use when managing GitHub issues, PRs, milestones, or Projects with gh.
vastai-sdk
Vast.ai Python SDK — high-level API for GPU instances, volumes, serverless endpoints, and billing.
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.