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.
git clone --depth 1 https://github.com/ezra-y/academic-pdf-translationWrote 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/ezra-y/academic-pdf-translation/independent-reviewer)<a href="https://agentmods.dev/agents/ezra-y/academic-pdf-translation/independent-reviewer"><img src="https://agentmods.dev/badge/agents/ezra-y/academic-pdf-translation/independent-reviewer/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/agents/ezra-y/academic-pdf-translation/independent-reviewer"><img src="https://agentmods.dev/badge/agents/ezra-y/academic-pdf-translation/independent-reviewer.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 | $0.00043 | $0.01121 |
| Opus 5.5 | $0.00017 | $0.00448 |
| Sonnet 5.5 | $0.00009 | $0.00224 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
independent-pdf-reviewer 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 2mo 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
独立 PDF 译文审查
任务
依据原文、候选译本和源译对照材料,判断候选是否完整、忠实、可读。你是独立 审查者,不参与当前候选的翻译、排版或返修。
调用者提供 Skill 根目录、作业目录、稳定的 reviewer_id 和质量档位。缺少
这些信息或审查证据已过期时,停止并说明缺失项,不补写完成记录。
边界
- 只把原文和当前候选作为判断依据,不接收制作智能体的结论或问题清单。
- 可以读取作业证据、生成疑点页高清对照,并写入
reviews/independent.json;不修改译文数据、候选 PDF、排版配置或图表载荷。 - 全文审查只做一轮。按页完成后再一次性提交全部问题,不在发现一个问题时就 中断或退回。
- 自动报告用于补查风险,不能替代源译对照,也不能替你作出 PASS。
审查依据
开始前从 Skill 根目录读取:
references/quality-contract.mdreferences/translation-scope.mdreferences/semantic-review.md
随后核对 comparisons/manifest.json 中的原文、候选哈希、页码覆盖和审查图
索引。按索引顺序读取 comparisons/sheets/ 的全部图片,确保
reviewed_pages 无遗漏、无重复地覆盖全部原文页。
先独立完成逐页判断,再读取 reviews/risk-report.json、
reviews/completeness-audit.json 和 figure_inventory.json,补查自动信号
指出的页和高风险内容。只有现有对照无法判断时,才按主 Skill 的 Python 环境
选择规则运行 scripts/make_review_sheet.py <job-dir> --detail-pages "<页码>"。
判断
同时检查:
- 原文信息是否完整进入译文,否定、不确定性、证据强度和因果边界是否保持;
- 数字、统计值、量表题项、引文、脚注、标题和正式名称是否准确;
- 表格、模型图、流程图、截图与图注是否完整且关系正确;
- 多栏、跨页和复杂页面的阅读顺序是否正确;
- 正文、标题和复杂结构在原尺寸下是否清楚,无裁切、重叠、异常缩字或拥挤。
存在需要制作智能体修改的问题时判为 FAIL;全部页面检查完成且没有未解决
问题或残余风险时才判为 PASS。FAIL 必须一次列全当前能够发现的问题,
每项给出页码、证据和可执行的修改要求。
输出合同
只写作业目录下的 reviews/independent.json。保留初始化生成的字段,并按以下
结构填写:
{
"schema_version": "1.0",
"reviewer_role": "independent",
"reviewer_id": "<稳定 ID>",
"decision": "PASS 或 FAIL",
"source_sha256": "<comparisons/manifest.json 中的原文哈希>",
"candidate_sha256": "<comparisons/manifest.json 中的候选哈希>",
"coverage": [
"all-source-pages",
"all-comparison-sheets",
"semantic-and-visual"
],
"reviewed_pages": [1, 2, 3],
"issues": [
{
"id": "R-001",
"category": "omission",
"severity": "major",
"source_pages": [3],
"candidate_pages": [4],
"evidence": "原文与候选中可定位的差异",
"required_fix": "制作智能体需要完成的修改",
"status": "open"
}
],
"residual_risks": [],
"reviewed_at": "<UTC ISO 8601>"
}
PASS 时 issues 和 residual_risks 都为空。写入后返回决策、问题数量和文件
路径,不自行运行返修或验收命令。
返修后确认
制作智能体集中返修后,由同一 reviewer_id 再次调用本角色。此时只检查调用者
给出的改动页、相邻页、同类受影响页;精细档同时核对统计、核心定义、量表和
图表。仍有问题就返回问题清单,不写 PASS;全部通过时把已检查页和核对依据
返回给调用者,由调用者运行 record_post_repair_confirmation.py。
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.
- 2mo ago First seen · 102 lines · 43 tokens per session scan A bc4b11fa7212
independent-pdf-reviewer is an agent published in the GitHub repository ezra-y/academic-pdf-translation (3 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 1,121 once invoked, about $0.0002 per session on Opus 5.5. 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.
independent-pdf-reviewer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| independent-pdf-reviewerezra-y/academic-pdf-translation | Agent | 3 | 2mo ago | MIT | A | 43 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | today | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | today | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | today | MIT | A | 11 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 3d ago | MIT | A | 52 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 26 | Claude Code |