Borrowing it
Nothing to install: this file belongs to sollawen/microNeo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sollawen/microNeo/master/.agents/skills/changelog/SKILL.mdgit clone --depth 1 https://github.com/sollawen/microNeoWrote 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/sollawen/microneo/changelog)<a href="https://agentmods.dev/skills/sollawen/microneo/changelog"><img src="https://agentmods.dev/badge/skills/sollawen/microneo/changelog/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/sollawen/microneo/changelog"><img src="https://agentmods.dev/badge/skills/sollawen/microneo/changelog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.00837 |
| Opus 5 | $0.00016 | $0.00418 |
| Sonnet 5 | $0.00006 | $0.00167 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
changelog 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.
What it actually says
Core principle
只讲用户可见的功能变化,不写技术实现细节。
用户读 changelog 是想知道「这个版本我能用到什么新东西、什么变了、什么修好了」。实现层面用了什么 sentinel、归一化放哪一层、调了哪个内部函数 —— 这些属于 commit message 和设计文档,不属于 changelog。
判断标准:
- 如果一个变化用户在界面上看不到、操作不到、感知不到,它通常不该单独占一条 changelog bullet。
- 较大规模的内部重构值得记一条(放 Changed),让读者了解架构演进和潜在的升级影响;琐碎重构不记。
Format (hard constraint)
## [X.Y.Z] - YYYY-MM-DD —— 方括号、无 v 前缀、ISO 日期。
这是硬约束:tools/extract-changelog.sh 用 substr($0,1,5+len(v)) == "## [" v "]" 精确匹配来提取 release notes。格式错了 release workflow 会失败。
- 新版本条目插在最顶部(最新在上)。
- 日期用该版本最后一个 commit 的日期。
- 分类用加粗 heading,顺序:Added → Changed → Fixed → Removed → Docs。用不到的分类直接省略,不要留空 heading。
Bullet writing
- 一条 bullet = 一个变化。动名词或名词开头,先说「是什么」再说「有什么用」。
- 句尾可点一句用户价值(为什么 / 解决了什么),但不要展开怎么做。
- 命令、配置项、文件名用反引号。
- 较大规模的内部重构(即使无用户可见行为变化)应记入 Changed,一句话点明重构的范围和动机(如「重构 X 模块以提升 Y」),不写实现细节;琐碎重构不记。
反例(实现细节泄漏,不要这样写)
SelectPane.OpengainsmaxVisible+wrapparams. Overflowing lists scroll with▲▼indicators drawn in the right padding column.FloatFrameis unchanged — scrolling is the concrete popup's business, not the framework's.FloatFrame.Opennormalization lives inOpen(input layer), not in the pure-geometryexpandAnchor; existing callers passingY >= 0are unaffected.
正例(只讲用户能感知的)
- SelectPane supports list scrolling (with
▲▼overflow indicators) and caller-configured viewport height / wrap behavior.- FloatFrame supports bottom-anchored popups via negative
anchor.Y, so popups can snap to just above the status line.
Workflow
git log <last-tag>..HEAD --format='%h | %ad | %s' --date=short列出待发布提交。- 按 Added / Changed / Fixed / Removed / Docs 归类(docs: / chore: 前缀的多数进 Docs 或省略)。
- 必要时
git show <hash>看提交正文确认变化的用户面(不是实现面)。 - 在 CHANGELOG.md 顶部插入新
## [X.Y.Z]段。 - 拿不准一条要不要写时,默认不写 —— changelog 宁精勿滥。
- 如果仅是修改了changelog.md的时候,不要commit
Language
English only.
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 · 55 lines · 32 tokens per session scan A 5d5030c5a9d9
changelog is a skill published in the GitHub repository sollawen/microNeo (55 stars, last pushed 23d ago), licensed MIT. It adds 32 tokens to every session and 837 once invoked, about $0.0002 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
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
gh-credit-harvest
Harvest one community PR into a release branch with authorship and credit preserved, verified green, and a warm thank-you.
release
Skill "release" from Hmbown/Codewhale, covering release, invocation, non-goals and workflow.
writing-git-commits
Write clear, focused Git commit messages and keep commits easy to review.
od-plugin-publish-github
Publish a local Open Design plugin to a new public GitHub repository using gh CLI.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.