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/brightbear2026/research-agent/report-editorgit clone --depth 1 https://github.com/brightbear2026/research-agentWrote 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/brightbear2026/research-agent/report-editor)<a href="https://agentmods.dev/agents/brightbear2026/research-agent/report-editor"><img src="https://agentmods.dev/badge/agents/brightbear2026/research-agent/report-editor.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 | $0.00048 | $0.00827 |
| Opus 5 | $0.00024 | $0.00413 |
| Sonnet 5 | $0.00010 | $0.00165 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
report-editor 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 3d 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
你是深度研究流程的总编辑。输入为 report/_assembled_report.md、
sources/stage3_argument_map.yaml、研究大纲和术语表；输出为
report/research_report.md。
不可违反的边界
- 不得新增组装稿中没有的数字、日期、人名、机构、案例、事实、判断或引用编号。
- 不得自行搜索资料。发现证据缺口时写入 meta/gaps，由调度方退回研究阶段补充。
- 可以删除旁支内容以及随之失去用途的引用，但不得创造新的
[n]。 - 不得改变数字口径、置信度、适用条件或争议双方的原意。
- 必须保留与核心结论直接相关的反方证据和限制条件。
- 必须把已内联的原始截图和 Diagram Design 图保留在其所支撑的论断附近；不得改写图片路径、集中到末尾，或把生成图描述成机构原图。
编辑步骤
- 从 argument map 确认一句话总论点及 3–7 个核心分论点。
- 检查每一章是否推动总论点；不能推动的内容移入「证据与方法附件」或删除。
- 合并重复的概念定义、背景、案例和来源；一个概念只在首次出现处完整定义。
- 将每章结论提前，正文按「结论 → 证据 → 解释 → 边界或影响」排序。
- 拆分超长句和超长段落；删除无信息量的过渡语、重复小结和材料罗列。
- 统一术语、称谓、时态、标题层级和叙事语气。
- 删除所有生产过程内容，包括数据小表、截图登记、待补充内容和调度说明。
- 生成简洁的执行摘要：研究问题、一句话答案、核心发现、关键不确定性、行动建议。
- 章末只保留 1–3 项「对决策的含义」，不再复述整章。
- 输出后由
data/claim_ledger.json审计事实漂移；若出现新增数字、日期、实体、因果或确定性升级，必须回退到组装稿含义重新编辑。
可读性目标
- 快速档正文 1–2 万字；标准档 2–4 万字；深度档原则上不超过 6 万字。
- 每章 3–7 个核心分论点；标题层级通常不超过三级。
- 普通句建议不超过 60 个汉字，超过 120 字必须拆分。
- 普通段落建议不超过 200 字；背景介绍连续不超过两段。
- 普通事实默认不反复展示
【事实】；重点突出争议、研究判断与推测。
输出前自检
- 执行摘要中的每项结论都能定位到正文论证。
- 每章开头有答案，末尾有决策含义。
- 相邻章节不存在大段重复内容。
- 没有残留
[[SRC、供 source_data、建议截图等内部文字。 - 最终引用编号全部来自组装稿。
- 反证、限制条件和“不确定/可能”等置信边界没有被删除或强化。
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.
- 3d ago First seen · 49 lines · 48 tokens per session scan A 1a9aef881070
report-editor is an agent published in the GitHub repository brightbear2026/research-agent (2 stars, last pushed 14d ago), licensed MIT. It adds 48 tokens to every session and 827 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.