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 lupingluke-ai/general-ai-spec --skill change-dispatchgit clone --depth 1 https://github.com/lupingluke-ai/general-ai-specWrote 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/lupingluke-ai/general-ai-spec/change-dispatch)<a href="https://agentmods.dev/skills/lupingluke-ai/general-ai-spec/change-dispatch"><img src="https://agentmods.dev/badge/skills/lupingluke-ai/general-ai-spec/change-dispatch/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/lupingluke-ai/general-ai-spec/change-dispatch"><img src="https://agentmods.dev/badge/skills/lupingluke-ai/general-ai-spec/change-dispatch.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 | $0.00071 | $0.07625 |
| Opus 5 | $0.00036 | $0.03812 |
| Sonnet 5 | $0.00014 | $0.01525 |
| Haiku 4.5 | $0.00007 | $0.00762 |
Grade A, and why
change-dispatch 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 10d 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 — 534 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Change Auto-Dispatch
Overview
自动扫描并领取就绪的 OpenSpec 任务组。Runner 无关表示协议不绑定某一种 agent;执行环境仍必须具备项目声明的 Node/pnpm/技术栈工具链、agent CLI、模型凭据、GitHub 写权限和网络访问。
三层解耦:
- Runner 层(谁触发 dispatch 运行):cron /
/loop Nm /change-dispatch/ Codex Automation / GitHub Actions / 人工一次性触发,任选其一 - Dispatch 逻辑层(本 skill):扫描 → 认领 → 实现 → push,不关心是谁在跑
- Executor 层(每个任务组用什么执行模式):tasks.md 任务组注释的
执行模式:tag 决定;dispatch 兼容旧执行工具:tag
Branch-Centric 模型: 四件套和实现代码都在 feature branch 上。dispatch 通过 main 上的 backlog 索引找到活跃 change,fetch 对应 feature branch 读取 tasks.md,实现后直接 push。
Announce at start: "Running change-dispatch: scanning for ready task groups."
Bash 命令规范
为兼容 Claude Code / Codex 等不同执行环境的权限与审批模型,所有 Bash 操作必须遵循:
- 每条命令独立调用 — 不在一条 Bash 中用
&&、||、;串联多条命令 - 管道可以用 — 单条命令内的管道(如
git branch -r | grep feat/)是允许的 - 并行无依赖时分开调用 — 多条独立命令应作为多个并行 Bash tool call 发送
示例:
# ❌ 错误:复合命令触发确认
git fetch origin && git branch -r | grep feat/ && gh pr list --state open
# ✅ 正确:拆分为独立调用
# Call 1: git fetch origin
# Call 2: git branch -r | grep feat/
# Call 3: gh pr list --state open --json number,headRefName,title,isDraft
类型 → 分支/提交前缀映射规则
type 的事实源是 product/backlog.md 的类型列(dispatch Step 1 扫描 backlog 时同一行直接读到,无需从 change-id 字符串反解析)。由 type 映射 branch / commit 前缀:
| type | branch 前缀 | commit type |
|---|---|---|
| feature | feat/ |
feat |
| bug | fix/ |
fix |
| chore | chore/ |
chore |
| hotfix | hotfix/ |
fix |
<branch-prefix> 和 <commit-type> 全流程复用,禁止硬编码 feat/。4 种类型走相同的 dispatch 路径,无例外。
change-id 的命名前缀(
fix-/chore-/hotfix-)由prd-writer按 type 生成、change-propose校验,仅作语义标签;dispatch / review 不解析它。
Runner 配置(任选其一)
dispatch 对 runner 的要求包括:git、shell、项目技术栈工具链、依赖安装能力、可调用本 skill 的 agent CLI、模型凭据、GitHub 写权限和网络。触发频率由项目自行配置,需保证不会长期占用分支或压垮 CI。
方式 A — Claude Code /loop(推荐开发期)
/loop <interval> /change-dispatch
优点:零配置;启动/停止方便;可与 change-propose / change-review 的人工或定时触发协作。
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.
- 10d ago First seen · 534 lines · 71 tokens per session scan A 51dd1149e8fa
change-dispatch is a skill published in the GitHub repository lupingluke-ai/general-ai-spec (5 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 7,625 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 2026-08-31.
Other skills, from other repositories
openspec-bulk-apply-change
Use when multiple active OpenSpec changes should be applied concurrently in isolated worktrees with delegated verification and no merge.
openspec-bulk-apply-change
Use when multiple active OpenSpec changes should be applied concurrently in isolated worktrees with delegated verification and no merge.
ucx-github-governance
Hermes governance skill for GitHub issue and PR lifecycle control aligned to governance/GOVERNANCERULES.md and UCX V3 round-based gate policy.
cflx-run
Run the standard Conflux development flow for an already-defined and committed OpenSpec change. Use when users want to execute cflx run, start Conflux orchestration, or follow the standard proposal-then-run workflow on a clean base branch.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.