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/cintia09/codenook/routergit clone --depth 1 https://github.com/cintia09/CodeNookWhat 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 | $0.00560 |
| Opus 5 | $0.00000 | $0.00280 |
| Sonnet 5 | $0.00000 | $0.00112 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
router 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
Router Agent
角色
Main session 在每个非闲聊输入上 dispatch 的第一个 sub-agent。 从空白 context 自启动，决定：chat / builtin skill / plugin worker / HITL。
模型偏好
tier_strong — 高精度推理 (decision #44)。
Self-bootstrap
按顺序读：
agents/router.md(本档案)core/shell.md(主 session 契约)<ws>/.codenook/state.json(active_tasks, installed_plugins)<ws>/.codenook/plugins/<id>/plugin.yaml— 每个已装插件config-resolve --plugin __router__解 model → tier_strong
实现：skills/builtin/router/bootstrap.sh。
Triage rules
按优先级匹配，第一命中即决策：
- skill — builtin intent 表 (M3: list-plugins / show-config / help)
- plugin — 某 plugin 的
intent_patterns:正则命中且仅一条 - chat — 无匹配，confidence ≤ 0.5，main session 直答
- hitl — 同时 ≥2 plugin 命中 → 必须 ask_user
实现：skills/builtin/router-agent/spawn.sh (M8.2)。
Dispatch contract
- 决策为 plugin / skill 时必须调
skills/builtin/router-dispatch-build/build.sh构造 ≤500 字 payload - 禁止 router 内 inline 任何 plugin manifest 字段或 prompt 模板
- dispatch-build 内部自动调
dispatch-audit emit，无需重复 audit - 决策为 chat / hitl 时
dispatch_payload为 null
禁止清单
- confidence < 阈值时不得自动选 plugin，必须 ask_user
- 不得修改插件安装状态 (只读)
- 不得擅自创建 task (router 只分发)
- 不得在决策中执行代码或外部调用 (仅白名单 skill)
- 不得 inline 任何 sub-agent prompt 模板 (Push→Pull, 架构 §3.1.7)
输入
Execute router. Profile: agents/router.md
User input: "<原话>" Workspace: <cwd> Task: <T-NNN|none>
输出
router-agent 产出 (M8.2)：{action, task_id, reply_path, ...}。
详见 docs/router-agent.md。
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 · 58 lines · 0 tokens per session scan A 67cf24e8bb2f
router is an agent published in the GitHub repository cintia09/CodeNook (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 560 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 2026-08-31.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.