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/deeflect/dory/2026-04-20-relay-handoffgit clone --depth 1 https://github.com/deeflect/doryWhat 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 | $0.00089 |
| Opus 5 | $0.00000 | $0.00044 |
| Sonnet 5 | $0.00000 | $0.00018 |
| Haiku 4.5 | $0.00000 | $0.00009 |
Grade A, and why
2026-04-20-relay-handoff 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 yesterday.
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
Relay handoff
Demo Agent Ada found that Relay parser failures were caused by missing fenced-code terminators in synthetic notes.
Demo Agent Ben added a validator reminder and source-hit counters to the handoff checklist.
The final Relay handoff says to keep chunked summaries short, preserve source-hit counters, and flag malformed markdown before indexing.
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.
- yesterday First seen · 14 lines · 0 tokens per session scan A f87159b13935
2026-04-20-relay-handoff is an agent published in the GitHub repository deeflect/dory (11 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 89 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
skills-management
Skill 是一个可复用的能力包，通常包含一个 SKILL.md、提示词、参考资料和可选脚本。智能体先看到 Skill 的描述，再按需要读取 SKILL.md；Skill 声明的工具和 MCP 依赖会随激活状态加入模型请求。.
agent-request-queue
一次 Agent 运行可能包含多次模型调用、知识库检索、工具执行和文件操作。为了避免同一对话同时修改同一份上下文，Yuxi 把“收到请求”和“开始运行”分成两个阶段，并为每个线程维护 FIFO 队列。.
tools-system
Yuxi 的工具分成三层：内置工具、知识库工具和 MCP 工具。Graph 创建时准备可执行工具，运行时再根据用户权限、Agent 配置和 Skill 激活状态决定模型能看到什么。.
agent-evaluation
智能体评估用 Langfuse Dataset 保存一组固定任务，再让 Yuxi 按真实的 AgentRun、worker 和工具链路逐条执行。它适合比较一个智能体在研究、编程、文件处理或多步骤任务上的表现。.
agents-config
本页是智能体配置参考，说明页面上的字段如何进入一次运行。新增智能体后端的代码结构见开发智能体后端；只使用现成智能体时，从快速开始开始。.
mcp-integration
MCP（Model Context Protocol）让智能体调用外部服务提供的工具。管理员在“扩展 → MCP”中添加远程服务器，智能体配置再决定哪些服务器进入运行时。.