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/demondamon/agenticx/conclusiongit clone --depth 1 https://github.com/DemonDamon/AgenticXWhat 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 | $0.02383 |
| Opus 5 | $0.00000 | $0.01192 |
| Sonnet 5 | $0.00000 | $0.00477 |
| Haiku 4.5 | $0.00000 | $0.00238 |
Grade A, and why
conclusion 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 2d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agents目录完整结构分析
目录路径
d:\myWorks\AgenticX\examples\agenticx-for-intent-recognition\agents
统计信息
- 总文件数:6
- 总大小:54,707 字节 (0.05 MB)
完整目录结构
目录结构: d:\myWorks\AgenticX\examples\agenticx-for-intent-recognition\agents
==================================================
├── __init__.py (638 bytes)
├── function_agent.py (17,532 bytes)
├── general_agent.py (8,628 bytes)
├── intent_agent.py (10,071 bytes)
├── models.py (3,629 bytes)
└── search_agent.py (14,209 bytes)
详细文件内容分析
init.py
- 文件大小:638 字节
- 文件类型:.py
文件功能:作为 agents Python包的入口,汇集并暴露了所有核心的数据模型和Agent类,简化了外部调用。
技术实现:通过 from .module import ... 语法导入包内其他模块的类,并使用 __all__ 列表明确定义了包的公共API。
关键组件:__all__ 列表,其中包含了所有公开的类名。
业务逻辑:该文件是典型的Python包初始化文件,其核心作用是构建一个统一的、清晰的门面(Facade),让使用者无需关心内部模块的具体划分,可以直接从 agents 包中导入所需的一切。
依赖关系:依赖于同级目录下的 models.py, intent_agent.py, general_agent.py, search_agent.py, function_agent.py。
models.py
- 文件大小:3,629 字节
- 文件类型:.py
文件功能:定义了整个意图识别模块所需的核心数据结构,确保了数据在不同Agent之间的传递时具有一致性、可校验性和类型安全性。
技术实现:使用 pydantic.BaseModel 定义了强类型的配置和数据模型,如 AgentConfig, IntentContext, IntentResult, Entity。使用 enum.Enum 定义了 IntentType,规范了意图的分类。
关键组件:IntentType 枚举, Entity, IntentResult, IntentContext, AgentConfig Pydantic模型。
业务逻辑:此文件是整个系统的基石。通过标准化的数据模型,它为Agent的输入(IntentContext)、输出(IntentResult)以及配置(AgentConfig)提供了统一的规范,极大地提高了代码的健壮性和可维护性。
依赖关系:主要依赖 pydantic 和 enum 库。
intent_agent.py
- 文件大小:10,071 字节
- 文件类型:.py
文件功能:定义了意图识别的基础Agent类 IntentRecognitionAgent,作为所有具体意图Agent的父类,实现了与大语言模型(LLM)交互的核心逻辑。
技术实现:继承自 agenticx.core.Agent,使用 agenticx.llms.KimiProvider 与LLM通信。它通过格式化提示词(Prompt)将用户输入发送给LLM,并负责解析返回的JSON结果。包含一个基于关键词的 _fallback_intent_recognition 方法,用于在LLM解析失败时提供基础的识别能力。
关键组件:IntentRecognitionAgent 类,recognize_intent 方法,_parse_llm_response 方法。
业务逻辑:这是意图识别流程的“大脑”。它负责调用LLM的通用智能来对用户输入进行初步分类(通用对话、搜索、工具调用)。它定义了整个识别流程的框架,并为特定意图的精细化处理提供了扩展点。
依赖关系:依赖 agenticx 框架、json, time 库以及本地的 .models 模块。
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.
- 2d ago First seen · 117 lines · 0 tokens per session scan A 0e885ca52730
conclusion is an agent published in the GitHub repository DemonDamon/AgenticX (219 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,383 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
ai-output-code-review-super-auditor
Agent "ai-output-code-review-super-auditor" from alfredolopez80/multi-agent-ralph-loop, covering the vision, your work, step by step, ultrathink principles in practice, 0. role & mission and 1. scope of work.
prompt-optimizer
Agente que transforma prompts ordinarios en prompts profesionales para IA usando arquitectura en 5 capas.
gap-analyst
Analyzes feature requests for missing requirements, edge cases, and ambiguities BEFORE implementation. Prevents rework by finding gaps early.
senior-frontend-developer
Agent "senior-frontend-developer" from alfredolopez80/multi-agent-ralph-loop, covering the vision, your work, step by step, ultrathink principles in practice, role & persona and operating mode.
autoresearch
Autonomous researcher - iteratively modifies code, runs experiments, evaluates metrics, keeps improvements. Never stops unless budget exhausted or manually interrupted.
plan-sync
Synchronizes downstream plan steps after implementation drift. Spawned by orchestrator after each step completes to patch stale references.