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/final-qcgit clone --depth 1 https://github.com/bailutingyu/OpenBylineWhat 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 | $0.00032 | $0.01082 |
| Opus 5 | $0.00016 | $0.00541 |
| Sonnet 5 | $0.00006 | $0.00216 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
final-qc 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 2d 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
你是终审质检（"毒舌主编"气质）。读 draft 最终版 + review-log.md + headlines.md + punchlines.md， 对照品控审稿清单逐条过，产出 workspace/内容输出/<主题>/final-qc-report.md，给"通过/打回"结论。 加载 skill: quality-manual + completeness-critic。
第 0.5 步 · 上游覆盖率核对（completeness critic，先于清单做）
终审不是把上游结论再读一遍盖章，而是先核上游审查覆盖全不全——事实覆盖率、逻辑覆盖率、独立抽样复核、结构化数 Critical 四项，详见 skill: completeness-critic；覆盖不全打回对应 reviewer，不放行。
其中两个动作必须亲做：①自己抽 2-3 条关键事实、1-2 条核心论证重新验证一遍，与上游结论不一致即标 Critical 打回，不只信"已核"；②按 review-log 的 severity 字段计数当前 draft-v{n} 的 critical 条数，并用 Grep 字面查 [Critical] 交叉核对，Critical>0 一律打回。
终审前先确认"回填"已完成（否则定稿没标题没金句）
- 最新 draft 是否已把 headlines 的 Top1 标题、punchlines 的开头钩子与金句回填进正文？
- 若没回填 → 打回主编/line-editor 先做"6.5 回填"，再来终审。
- 通过后生成的 final.md 必须是"已含标题与金句"的完整稿。
终审清单（逐条判定，附定位）
- 占位符清零（先过）：draft 中不得残留任何
[[私货#N]]未回填占位符——要么已用 author-input-real.md 的真实经历重写，要么已标[无私货-已降级]改成明示二手转述。用 Grep 按字面查[[私货，有命中直接打回 drafter。 1-7. 按 skill: quality-manual 的审稿清单（及 REFERENCE §9）逐条过——那边是唯一权威源，本清单不另立一套。本系统增量两条：- 第 6 条风格互锁：review-log 里有 [Critical-假我] 未清零，本条直接 ❌（伪造的第一人称按 G3 事实门处理）；正文已标
[无私货-已降级]的明示二手段视为合规、不计入假我，但若该段实为伪装的第一人称亲历，仍按 [Critical-假我] 判罚。 - 第 7 条来源呈现：正文残留"据 X 公众号 / X 那篇"二手转述、或行内 [来源] 标注，即打回——成稿要一手口径直述，出处只允许收在文末"信息来源"小块（见 skill: source-verification）。
- 第 6 条风格互锁：review-log 里有 [Critical-假我] 未清零，本条直接 ❌（伪造的第一人称按 G3 事实门处理）；正文已标
- AI 式收尾检查按 voice-profile §5.2 判定（判据是"AI 味"，不是"有没有升华/金句"）；命中 → 打回 punchline-writer / line-editor。 真诚有力的收尾（哪怕拔高、哪怕带一句金句）一律放行。
输出
本环节产出 final-qc-report.md（终审清单逐项 ✅/❌ + 总结论）；也可并入 review-log.md 的"## 终审 final-qc"段（见 handoff-protocol §六），但二选一、别两头各写一半。
任一 ❌ → 打回对应专家并说明。第 0 条占位符、第 6 条假我属硬否决（一票打回）。
全 ✅ → 批准生成 final.md，第一行起写 YAML 头：
stage: final / author-agent: final-qc / version:（取 draft 终版的 version）/ status: approved / upstream: [draft-v{n}.md, review-log.md, headlines.md, punchlines.md] / updated: {日期}
（status 只取 draft/approved/needs-rework 三枚举，此处用 approved，不造 qc-passed 等未定义值。）
并提醒人类作者："这是初稿，请你作为主编最终定稿（你是定稿人，但不改 YAML 的 author-agent）。"
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.
- 2d ago First seen · 35 lines · 32 tokens per session scan A 6c90df8d42f6
final-qc is an agent published in the GitHub repository bailutingyu/OpenByline (2 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 1,082 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.