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-proposegit 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-propose)<a href="https://agentmods.dev/skills/lupingluke-ai/general-ai-spec/change-propose"><img src="https://agentmods.dev/badge/skills/lupingluke-ai/general-ai-spec/change-propose/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-propose"><img src="https://agentmods.dev/badge/skills/lupingluke-ai/general-ai-spec/change-propose.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 | $0.00060 | $0.05540 |
| Opus 5 | $0.00030 | $0.02770 |
| Sonnet 5 | $0.00012 | $0.01108 |
| Haiku 4.5 | $0.00006 | $0.00554 |
Grade A, and why
change-propose 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 — 415 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Change Propose
Overview
从 approved PRD 出发，生成四件套（proposal + delta specs + design + tasks），创建 feature branch 和 Draft PR，并通过 governance PR 更新 main 索引。
职责边界： 只负责 propose 阶段。执行由 change-dispatch，审查/归档由 change-review 各自独立完成。
Announce at start: "Running change-propose: looking for changes to propose."
Bash 命令规范
- 每条命令独立调用 — 不用
&&、||、;串联 - 管道可以用 — 如
git branch -r | grep feat/ - 并行无依赖时分开调用 — 多个独立 Bash tool call
PRD YAML 前置条件
---
id: PRD-NNN
type: feature | bug | chore | hotfix
backlog-ref: B-NNN
module-ref: M-NNN # 必填；归属模块
status: approved
created: YYYY-MM-DD
depends-on: [B-xxx, B-yyy] # 前置 backlog 依赖，无则 []
change-id: kebab-case-name # 预定义 change-id，按类型携带前缀
design-inputs: # 必填；至少包含模块文档路径
- design/modules/M-NNN-<slug>.md
# - design/inputs/...（可选追加）
---
自动扫描时，缺少 type、depends-on、change-id、module-ref 或 design-inputs 的 PRD 会被跳过；显式 /change-propose B-NNN 命中这些问题时 STOP 并写日志。design-inputs 必须包含一条指向 design/modules/<M-NNN>-*.md 的路径，否则视为缺失。
类型 → 分支/提交前缀映射规则
backlog / PRD 的 type 是声明事实源；change-id 的命名前缀由 prd-writer 按 type 生成（feature 无前缀 / bug fix- / chore chore- / hotfix hotfix-），本 skill 只做一致性校验。由 type 映射 branch / commit / PR 前缀：
| type | branch 前缀 | commit type | PR 标题前缀 |
|---|---|---|---|
| feature | feat/ |
feat |
feat |
| bug | fix/ |
fix |
fix |
| chore | chore/ |
chore |
chore |
| hotfix | hotfix/ |
fix |
fix |
Phase 0 必须验证：backlog type = PRD type，且 change-id 命名前缀与 type 匹配（type=bug 必须 fix- 开头、type=feature 不得携带 fix-/chore-/hotfix- 前缀等）。验证通过后，映射结果在 Phase 1/2 全程复用，禁止重新计算或硬编码 feat/。4 种类型走完全相同的执行路径，前缀差异仅用于语义标签（git log / release notes 过滤）。
Phase 0 — 目标选定
有参数（/change-propose B-045）
直接定位 product/backlog.md 中的 B-045 条目，读取对应 PRD。
无参数（/change-propose）
扫描 product/backlog.md，筛选满足全部条件的条目：
- 阶段为
exploring - 有 PRD 列值且 PRD 文件存在
- PRD
status: approved - PRD 有
type、change-id、depends-on、module-ref、design-inputs字段 design-inputs至少包含一条指向design/modules/<module-ref>-*.md的路径，且该文件存在- backlog type = PRD type，且 change-id 命名前缀与 type 匹配（prd-writer 生成规则）
depends-on中所有依赖条目阶段为done<branch-prefix>/<change-id>远程分支不存在，或远程分支已存在但 backlog 仍停留在exploring（发布恢复模式）
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.
- 11d ago First seen · 415 lines · 60 tokens per session scan A 32a56db9bbb4
change-propose is a skill published in the GitHub repository lupingluke-ai/general-ai-spec (5 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 5,540 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 2026-08-31.
Other skills, from other repositories
kn-handoff
Use when a feature crosses repository boundaries and one side must hand work to the other - generates a self-contained frontend-to-backend brief or backend-to-frontend API contract.
status
Display current FIRE project status and validate integrity of intents, work items, and runs.
run-plan
Plan the scope of a run by discovering available work items and suggesting groupings. Invoked before run-execute.
run-status
Display current run status and progress. Shows work item, mode, duration, and files changed.
openspec-bulk-apply-change
Use when multiple active OpenSpec changes should be applied concurrently in isolated worktrees with delegated verification and no merge.
cis-aws-compute-2.3
Ensure Tag Policies are Enabled.