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 AISEE-LAB/aisee-plugin --skill aisee-change-authorgit clone --depth 1 https://github.com/AISEE-LAB/aisee-pluginWrote 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/aisee-lab/aisee-plugin/aisee-change-author)<a href="https://agentmods.dev/skills/aisee-lab/aisee-plugin/aisee-change-author"><img src="https://agentmods.dev/badge/skills/aisee-lab/aisee-plugin/aisee-change-author/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/aisee-lab/aisee-plugin/aisee-change-author"><img src="https://agentmods.dev/badge/skills/aisee-lab/aisee-plugin/aisee-change-author.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 | $0.01781 |
| Opus 5 | $0.00051 | $0.00890 |
| Sonnet 5 | $0.00021 | $0.00356 |
| Haiku 4.5 | $0.00010 | $0.00178 |
Grade A, and why
aisee:change-author 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 9d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aisee:change-author
aisee:change-author 是单个 OpenSpec change 的详细文档 author。它读取当前 change 绑定的 schema、模板和已有文档,把该 schema 声明的各个文档写得更清晰、更完整、更不容易让后续开发出错。
它不是流程裁决器,也不是代码执行器。它的价值在于:按当前 schema 逐文档补齐高质量内容,并保持文档之间一致。
职责边界
负责:
- 只处理一个已确认边界和 schema 的 OpenSpec change。
- 读取当前 schema 的
schema.yaml、instruction、template、当前 change 目录和直接相关上游输入。 - 按 schema
artifacts[].requires的顺序生成或补齐文档。 - 先保留当前 schema 模板的章节和结构,再在模板基础上补强必要内容。
- 让每个文档都达到可执行、可审查、少歧义的粒度,而不是只填模板骨架。
- 在文档之间保持范围、术语、行为、约束、风险、验证方式和任务顺序一致。
- 对缺失前提、信息冲突、模板不足或边界不清的地方显式标 gap / blocker,而不是靠实现阶段临时猜。
- 已有文档存在时增量补齐,不覆盖用户已写内容。
不负责:
- 拆 change 边界、重新选择 schema、升级 schema 或一次处理多个 changes。
- 为 schema 未声明的文档创建文件。
- 写代码、生成实现代码、替代 review / test / archive。
- 把 planning docs、聊天记录或外部资料原样复制成 change 文档。
- 发明不在当前 change 和当前 schema 中的长期事实源。
输入门禁
开始 author 前必须确认:
- 当前只处理一个 OpenSpec change。
- change 已由
aisee:change-plan或用户明确确认边界、schema 和依赖。 - 能读取
openspec/changes/<change>/,或用户明确要求只输出草稿 / patch。 - 能读取当前 schema 的
schema.yaml和相关模板。 - 当前 change metadata 已声明 schema,且项目内已安装该 schema。
- 已收集与当前 change 直接相关的上游输入,例如 Change Plan、Issue、用户输入、SRS、baseline migration 结论或其它直接材料。
- 已读取项目规则:优先
AGENTS.md,CLAUDE.md只作为 legacy fallback。
如果 schema metadata 缺失、schema 未安装、模板缺失或当前 change 边界仍不清楚,输出 [CHANGE-AUTHOR-BLOCKED] 并列出缺口,不继续写文档。
CHECKPOINT
写入或修改任何 artifact 前,必须先给出以下摘要并等待用户确认:
- 当前 change
- 当前 schema
- schema 声明的文档顺序
- 计划生成 / 更新哪些文件
- 既有文档的合并策略
- 已发现的 blocker / gap / 风险
未确认时,只能输出 author 草稿、patch 预览或缺口报告,不直接写入 change 目录。
读取顺序
- 读取当前 schema 的
schema.yaml,确认 artifact DAG、模板位置和缺失项。 - 逐个读取本次会写到的 artifact 的
instruction和template。 - 读取当前 change 已有文档,理解用户已写内容和未完成部分。
- 读取与当前 change 直接相关的上游输入。
- 按 schema 声明顺序对每个文档执行
template pass -> strengthening pass -> local check。 - 完成后做一次一致性复检,确认文档之间没有明显冲突或漏项。
详细写法、逐文档边界、一致性检查、N/A 处理和编号规则见:
references/authoring-rules.md
Author 子阶段
schema preflight
-> change / schema / template / existing-doc check
document inventory
-> 确认本次要写哪些 schema 文档
detail pass
-> 逐文档先落模板骨架,再补齐目标、范围、行为、约束、风险、验证、实施顺序
local check
-> 检查当前文档是否既遵循模板,又补足了后续实现最容易出错的信息
consistency pass
-> 对齐术语、边界、前置假设、N/A、验证口径
final check
-> schema / template / cross-doc consistency recheck
What ships with it
3 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.
- 9d ago First seen · 141 lines · 103 tokens per session scan A 37b9744f68ff
aisee:change-author is a skill published in the GitHub repository AISEE-LAB/aisee-plugin (11 stars, last pushed 2mo ago), licensed MIT. It adds 103 tokens to every session and 1,781 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
openase-platform
Platform operations for tickets, projects, and runtime coordination inside OpenASE.
ticket-workpad
Maintain the persistent ticket work log comment on the current ticket and use it as the execution log.
workflow-authoring
Write workflow harness files that define role, status semantics, feedback loops, and durable delivery rules for disposable ticket workspaces.
task-breakdown
Turn a clarified spec into milestone-oriented tickets, dependency edges, and stage-gated delivery lanes.
auto-harness
Diagnose and strengthen a repository's harness layer: AGENTS.md rules, knowledge layout, architecture boundaries, lint and type gates, API and generated-client contracts, test scaffolding, structured logging, and technical-debt tracking. Use when Codex needs to audit drift-prone semantics that are repeated across…
deep-interview
Clarify ambiguous requests with a focused, Socratic interview before planning or implementation.