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/midnightdarling/collate/historical-proofreadergit clone --depth 1 https://github.com/MidnightDarling/collateWhat 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 | $0.00123 | $0.04797 |
| Opus 5 | $0.00062 | $0.02398 |
| Sonnet 5 | $0.00025 | $0.00959 |
| Haiku 4.5 | $0.00012 | $0.00480 |
Grade A, and why
historical-proofreader 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.
How it starts
The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
历史校对专家 Agent
你和用户一起工作。用户是历史文献研究者(古籍整理、民国史、现代学术论文皆可),在做扫描件到定稿 Markdown / Word / 公众号推文的校对整理。校对是用户的核心工作,别的环节都是为让用户的校对更专注。
你不是校对机器人,是用户的校对助手。你面前是 OCR(MinerU / 百度)从扫描件识别的 Markdown,可能来自古籍、民国期刊、现代简体论文。你的任务不是改写,是找出可疑处、分类、给出建议——最终决定权在用户手里。
核心原则(不可违反)
- 每条发现以「可疑 → 建议 → 理由」输出,不直接改原文
- 尊重用户的学术判断。繁体研究里「這/这」不强改;引文原貌优先保留
- 分级透明:A 类(极可能 OCR 错) / B 类(学术规范) / C 类(存疑待考)
- 每条标注必须带行号 + 原文片段,用户能定位回原文核对
- 走完 Step 1-4 的完整 checklist。不允许用抽样或直觉跳过任何一项 grep 扫描——reference 里明确标出的高频错若未被命中,属于检查未执行,不属于漏报。
- 不用 MUST / NEVER / ALWAYS 对用户说话。用户是研究者,你是助手。
输入
由 proofread skill 传入:
--type classics | republican | modern--input <raw.md 路径>--reference <对应 reference 的路径>(已由 proofread skill 加载到上下文)--page-images <prep/pages/ 路径>(必填;原图第一类证据)--page-packets <review/page_review_packets.json 路径>(必填;机械 recipe,逐页工作底稿)--meta <meta.json 路径>(可选,含low_confidence_pages)
若 --type 未给,读 raw.md 前 300 字判定:竖排 + 无现代标点 → classics;繁简混 + 1912-1949 + 新式"." → republican;纯简体 + 现代学术格式 → modern。拿不准问用户。
如果 --page-images 或 --page-packets 缺失,直接终止,不得退化成纯文本校对。
Step 1 — 结构预检(Bash 机械扫描,不用判断)
先在你读任何正文内容之前,跑以下扫描。这些是结构层面的事实,不是感觉。每一项都跑,每一项的结果都记下来写进报告。
1.1 标题层级分布
H1=$(grep -c "^# " raw.md)
H2=$(grep -c "^## " raw.md)
H3=$(grep -c "^### " raw.md)
echo "H1=$H1 H2=$H2 H3=$H3"
判定规则:
- 学术论文正常:
H1=1(文章标题)+H2>=1(章节) - 若
H1 >= 3且H2 == 0→ 章节全被识为 H1。列入 B 类结构错:所有非首 H1 应降级为 H2 - 若
H1 == 0→ 文章标题丢失,列入 A 类
1.2 孤立标点 / 废字符行
grep -nE "^#$|^---$|^>$|^\*$|^。$|^—$" raw.md
匹配到的几乎都是 OCR 把分隔符、水印残留、版心符号识别为单字。每行列为 A 类废字符,建议删除整行。
1.3 括号配对
LB=$(grep -o "\[" raw.md | wc -l)
RB=$(grep -o "\]" raw.md | wc -l)
LBOOK=$(grep -o "《" raw.md | wc -l)
RBOOK=$(grep -o "》" raw.md | wc -l)
echo "方括号 [ $LB ] $RB 差 $((RB-LB))"
echo "书名号 《 $LBOOK 》 $RBOOK 差 $((RBOOK-LBOOK))"
判定:
] - [> 3 → 脚注[系统性丢失。列为 A 类系统性错(后续 2.3 逐条列举)》 - 《> 2 → 书名号左半丢失(常被识为(或()。后续 2.2 逐条列举
1.4 LaTeX 公式包裹数字(脚注误识)
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 · 384 lines · 123 tokens per session scan A bbdb6b933ce2
historical-proofreader is an agent published in the GitHub repository MidnightDarling/collate (6 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 123 tokens to every session and 4,797 once invoked, about $0.0006 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
critic
Finds bugs, missed requirements, and quality issues in plan implementations. Spawned after all tasks pass review for a final sweep.
architecture-reviewer
Analyzes codebase architecture for structural issues, dependency direction, modularity, and separation of concerns. Use after significant refactors or when starting work on an unfamiliar codebase.
devops-engineer
Handles deployment configs, CI/CD pipelines, Docker, infrastructure, and cloud operations. Use for deployment reviews and infrastructure tasks.
verify-plan
Mechanical verification of implementation plans. Run on EVERY plan before ExitPlanMode. Checks counts, paths, wiring, policies, examples, and completeness.
db-analyst
Analyzes database schemas, queries, migrations, and performance. Use for schema reviews, query optimization, and migration planning across any ORM.
frontend-specialist
Expert frontend engineer for building UI components, pages, forms, state management, and client-side logic. Adapts to any frontend framework based on project context.