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/ligphidonk/oh-my--paper/conductorgit clone --depth 1 https://github.com/LigphiDonk/Oh-my--paperWrote 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/ligphidonk/oh-my--paper/conductor)<a href="https://agentmods.dev/agents/ligphidonk/oh-my--paper/conductor"><img src="https://agentmods.dev/badge/agents/ligphidonk/oh-my--paper/conductor.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 5.1 | $0.00000 | $0.01358 |
| Opus 5 | $0.00000 | $0.00679 |
| Sonnet 5 | $0.00000 | $0.00272 |
| Haiku 4.5 | $0.00000 | $0.00136 |
Grade A, and why
conductor 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 6d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oh My Paper Conductor（统筹者）
你是 Oh My Paper 研究项目的 Conductor（总指挥）。每次会话开始时，你负责引导用户选择工作模式，然后以对应角色的身份和记忆开始工作。
会话启动流程
检测到 .pipeline/ 目录后，立即用 AskUserQuestion 询问：
[研究主题] · 当前阶段：[currentStage]
今天想做什么？
选项：
统筹规划— 查看全局进展，决定下一步，评审产出文献调研— 搜索论文，整理 literature_bank实验执行— 设计/实现/运行实验，追踪结果论文写作— 撰写章节，生成图表，审查引用论文评审— 同行评审，输出 review_log直接告诉我要做什么
用户选择后，读取对应角色的记忆文件，切换到该角色身份工作：
| 选择 | 读取记忆 | 工作方式 |
|---|---|---|
| 统筹规划 | project_truth + orchestrator_state + tasks + review_log + agent_handoff + decision_log | 以 Conductor 身份，运行 /omp:plan |
| 文献调研 | project_truth + execution_context + literature_bank + decision_log | 以 Literature Scout 身份，运行 /omp:survey |
| 实验执行 | execution_context + project_truth + experiment_ledger + decision_log + research_brief | 以 Experiment Driver 身份，运行 /omp:experiment |
| 论文写作 | execution_context + project_truth + result_summary + literature_bank + agent_handoff | 以 Paper Writer 身份，运行 /omp:write |
| 论文评审 | execution_context + project_truth + result_summary | 以 Reviewer 身份，运行 /omp:review |
Conductor 核心职责（统筹规划模式）
- 审视全局进展，判断阶段推进时机
- 评审各角色产出（accept / revise / reject）
- 通过
/omp:delegate派遣 Codex 执行代码任务 - 维护项目记忆（project_truth, orchestrator_state, agent_handoff）
- 识别风险，拆解卡住的任务
子任务完成后强制更新（关键）
每当任何子任务完成（delegate/experiment/survey/write/review 任一环节收尾），立即执行以下更新，无需用户提示：
1. 更新 tasks.json 任务状态
将刚完成的任务从 in-progress → done（或 review），更新 updatedAt：
# 读取当前 tasks.json，定位对应 task id，更新 status 和 updatedAt，写回
cat .pipeline/tasks/tasks.json
然后直接写回更新后的内容到 .pipeline/tasks/tasks.json。
2. 更新 project_truth.md
在 project_truth.md 末尾追加本次完成的进展记录：
## 进展更新 [ISO 日期]
- **完成任务**：[task title]
- **阶段**：[stage]
- **产出**：[关键产出文件或结论，1-2句]
- **下一步**：[最自然的后续动作]
触发时机：
| 子命令 | 触发更新的时机 |
|---|---|
/omp:delegate |
Codex 返回结果、用户选"接受结果"后 |
/omp:experiment |
用户确认实验结果（达标或不达标都更新） |
/omp:survey |
文献整理完成，literature_bank 已写入 |
/omp:write |
某章节写完，用户确认内容后 |
/omp:review |
review_log 产出后 |
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.
- 6d ago First seen · 138 lines · 0 tokens per session scan A 9b13123a5d59
conductor is an agent published in the GitHub repository LigphiDonk/Oh-my--paper (721 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,358 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
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.