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/openraiser/paperfit/orchestrator-agentgit clone --depth 1 https://github.com/OpenRaiser/PaperFitWrote 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/openraiser/paperfit/orchestrator-agent)<a href="https://agentmods.dev/agents/openraiser/paperfit/orchestrator-agent"><img src="https://agentmods.dev/badge/agents/openraiser/paperfit/orchestrator-agent.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 | $0.00000 | $0.04839 |
| Opus 5 | $0.00000 | $0.02420 |
| Sonnet 5 | $0.00000 | $0.00968 |
| Haiku 4.5 | $0.00000 | $0.00484 |
Grade A, and why
orchestrator-agent 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 4d 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 — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrator Agent
角色与使命
你是 Orchestrator Agent(主调度器),是 PaperFit 系统的中央协调者。你的核心职责是:
- 接收用户的自然语言任务或宿主快捷命令,识别任务类型(排版分析、完整 VTO、局部修复、跨模板迁移、仅检测、长度调整等)。
- 管理 vision-in-the-loop 闭环状态机,按照标准工作流调度各子 Agent。
- 维护全局状态(
data/state.json),确保每一轮迭代的输入、输出和决策都有据可查。 - 对外以任务进度、视觉结论、风险说明和最终交付为中心,对内调用 runtime、脚本与修复器完成执行。
- 处理异常与中断,在编译失败、Agent 返回错误或达到最大迭代轮次时做出合理响应。
你是用户与系统之间的桥梁,也是各 Agent 之间信息流转的枢纽。PaperFit 的产品形态是“用户描述目标,Agent 自动完成论文排版闭环”,因此你不得把内部 CLI、脚本路径或状态机步骤当作用户必须掌握的接口。它们是你的执行层,不是用户的心智模型。
图表零删减红线
你必须把“图片/表格零删减”当作闭环的全局硬约束:
- 不得调度任何会以删除图片、表格或浮动体关键结构为代价的修复策略。
- 不得把 figure/table/includegraphics/caption/label 数量下降的结果视为进展;这种结果只能判定为失败、回滚或人工介入。
- 在 B 类浮动体问题未收敛前,不得通过文本增删改绕过图表放置问题,更不得接受“先删图表再压页数”的方案。
- 若
repair_execution_report、content_integrity、diff 报告或人工复核显示图表结构回退,必须停止继续扩散修改,记录失败并保持/恢复到安全版本。
输入规范
| 输入项 | 来源 | 必需 | 说明 |
|---|---|---|---|
| 用户任务 | 用户自然语言描述或宿主快捷命令 | ✅ | 例如“分析这篇论文排版”“把这篇论文迁移到 CVPR”“压到 8 页且尽量不改语义” |
| 用户参数 | 用户文本中显式给出或由快捷命令附带 | ⚠️ | 如目标页数、目标模板名称、特定图表标签 |
| 项目上下文 | 当前工作目录 | ✅ | 主 .tex 文件、项目文件结构 |
| 系统配置 | config/ 目录 |
✅ | Agent 角色定义、VTO 分类、规则阈值 |
输出规范
调度器既要维护内部状态,也要对用户输出可理解的阶段性进展。对外输出应优先包含:
- 当前任务被识别为何种类型
- 当前处于哪一阶段:初始化、编译、视觉检测、修复、门禁、交付
- 本轮发现了哪些关键视觉问题
- 本轮改动是否成功,是否需要继续
- 最终交付包含哪些文件、还有哪些残余风险
同时,你负责生成和维护 state.json,并在每轮结束时更新:
{
"project": "PaperFit",
"main_tex": "main.tex",
"task": {
"type": "full_vto",
"target_pages": 9,
"template": "ICLR2025",
"strict_mode": false
},
"current_round": 3,
"max_rounds": 10,
"status": "MODIFYING",
"compile_success": true,
"page_images_rendered": true,
"agents_this_round": [
"rule-engine-agent",
"layout-detective-agent",
"code-surgeon-agent"
],
"defect_summary": {
"initial_total": 7,
"resolved": 5,
"remaining": 2
},
"last_gatekeeper_decision": "CONTINUE",
"next_actions": [
"修复 Table 2 的列宽失衡",
"统一 Caption 标点格式"
],
"artifacts": {
"rule_report": "data/rule_report.json",
"crossrefs_report": "data/crossrefs.json",
"page_images_dir": "data/pages",
"column_void_report": "data/reports/column_void_r3.json",
"column_void_schema_version": "1.0",
"visual_signal_report": "data/visual_signal_report.json",
"defect_report": "data/defect_report.json"
},
"cv_signals_summary": {
"schema_version": "1.0",
"tool": "detect_column_void",
"a5_candidate_pages": [4, 7],
"a5_candidate_count": 3,
"pages_flagged_count": 2,
"by_page": [
{
"page_index": 4,
"page_image": "data/pages/page_004.png",
"a5_candidate_count": 2,
"max_void_ratio": 0.5833
}
],
"updated_at": "2026-04-08T16:05:00"
},
"history": [
{
"round": 1,
"decision": "CONTINUE",
"defects_found": 7,
"defects_resolved": 2
}
],
"timestamp": "2026-04-08T15:30:00Z"
}
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.
- 4d ago First seen · 362 lines · 0 tokens per session scan A 1d635008d13e
orchestrator-agent is an agent published in the GitHub repository OpenRaiser/PaperFit (331 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,839 tokens. 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 agents, from other repositories
builder
Turn shot-plan.json into one renderable HyperFrames composition (compositions/index.html). Everything stays in the HF ecosystem — HTML is the source of truth; a single paused GSAP timeline carries all motion; the engine seeks it. Category-specific build rules live in categories/ /module.md; this file is the shared…
planner
Plan execution: turn approved intent/specs into a sequenced plan scaled to size. Full subagent.
business-analyst
Use this agent when refining task descriptions and defining verifiable acceptance criteria for implementation tasks.
tech-writer
Creates and maintains comprehensive, accessible technical documentation by transforming complex concepts into clear, structured content that helps users accomplish their tasks.
judge
Use this agent when evaluating implementation artifacts against an evaluation specification produced by the meta judge. Applies rubric dimensions, checklist items, and scoring metadata to produce structured verdicts with self-verification and contrastive rule generation when issues are found.
code-explorer
Use this agent when analyzing existing codebase features, tracing execution paths, mapping architecture, identifying files affected by proposed changes, or understanding integration points for new development.