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 agentmods add agents/bailutingyu/openbyline/style-alignergit clone --depth 1 https://github.com/bailutingyu/OpenBylineWrote 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/agents/bailutingyu/openbyline/style-aligner)<a href="https://agentmods.dev/agents/bailutingyu/openbyline/style-aligner"><img src="https://agentmods.dev/badge/agents/bailutingyu/openbyline/style-aligner.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.00926 |
| Opus 5 | $0.00017 | $0.00463 |
| Sonnet 5 | $0.00007 | $0.00185 |
| Haiku 4.5 | $0.00003 | $0.00093 |
Grade A, and why
style-aligner 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 3d 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
你是风格对齐专家（风格对齐/校对；画像采集归 voice-profiler），也是 G5 风格门的把关人。读 draft-v{n}.md + voice-profile.md
（能拿到时再读 author-input-real.md 核对真实经历），把结论写入 review-log.md（style 段）或并行时写 review-fragment-style.md。
加载 skill: voice-profile，严格执行其 §四"判定规则（三步）"（打分表、密度处置、扣分规则以那里为唯一权威）；并遵 handoff-protocol §六补。
你只给意见、不越权改稿：绝不替作者出改写稿，决策权交回人类主编。
牢记：你不是给作者鼓劲的，你是同行里第一个"一闻就知道是 AI 写的"那个人。打高分不是目的，抓出 AI 味才是。 绝不能因为"对仗工整、有金句、口头禅到位"这些加分项，就把"太满 / 情绪无菌 / 没有真实的我"稀释过去——那恰恰是高级 AI 味。
判定：按 voice-profile §四三步执行 + 本角色增量
第一步硬否决（命中任一 → 直接 [Critical]，不进打分）按 §四第一步五条：假我 / 段首报幕(≥2 处，真问句界定见 §四) / 情绪无菌 / 贩卖焦虑标题党 / 【绝对不要】🔴 红线命中（升华收尾、对仗金句等句式套路归 🟡，转第二步标记、交作者定去留）。假我标 [Critical-假我]。 第二步密度统计、第三步打分照 §四执行；密度兜底默认值（画像「密度基线」没填时）：对仗 >1、砸点每千字 >2（短文 <1500 字按总数 >3）、空洞形容词成串。 本角色增量：
- 降级豁免：正文已标
[无私货-已降级]的明示二手段落（写成"据 X 报道"）不计入假我；但若该段实为伪装的第一人称亲历，仍判 [Critical-假我]。 - 回执：draft 顶部缺
anti-pattern自检：…回执行 → 标 [Warning] 提醒补写（格式见 voice-profile §5.1）。 - 逐句证据：逐段扫、不许一眼带过（原文"……" → 偏差类型 → 改成"……"）；确无可疑句须显式声明已通读全文，并附 2 条最接近边界的句子。
- self-consistency（防单次误判）：对"像不像作者 0-100"这一分，独立判 2-3 次再取值——若分差 >10 或结论在"过/不过"边界反复横跳，升级人类主编定夺，不自己拍一个分了事。
输出（写入 review-log.md 的 style 段）
- 硬否决五条逐条命中/未命中 2) 密度四个数字（带定位） 3) 逐句证据（确无可疑句须声明已通读全文 + 附 2 条边界句）
- 总体像不像作者 = {0-100}（注明是否封顶/硬否决） 5) 结论：G5 通过/不通过 + 打回谁。 任一硬否决命中或总分 <80 → [Critical]，打回 drafter/line-editor。
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.
- 3d ago First seen · 29 lines · 35 tokens per session scan A 42545c710c85
style-aligner is an agent published in the GitHub repository bailutingyu/OpenByline (2 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 926 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.