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/mindspore-ai/akg/specgit clone --depth 1 https://github.com/mindspore-ai/akgWhat 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 | $0.00451 |
| Opus 5 | $0.00000 | $0.00226 |
| Sonnet 5 | $0.00000 | $0.00090 |
| Haiku 4.5 | $0.00000 | $0.00045 |
Grade A, and why
SPEC 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.
What it actually says
core_v2/agents/ — Agent 开发规范
职责
定义 Agent 基类、继承体系和注册机制。
继承体系
AgentBase # base.py — 所有 Agent 的根
├── ReActAgent # react_agent.py — ReAct 循环 + 工具调用
├── PlanAgent # plan.py — 规划型 Agent
└── SkillEvolutionBase # skill_evolution_base.py — Skill 进化基类
关键文件
| 文件 | 说明 |
|---|---|
base.py |
AgentBase、Jinja2TemplateWrapper、LLMAPIError |
react_agent.py |
ReActAgent（继承 AgentBase，内置工具调用循环） |
plan.py |
PlanAgent |
skill_evolution_base.py |
SkillEvolutionBase |
registry.py |
AgentRegistry、@register_agent 装饰器 |
开发约定
新增 Agent 的标准流程
- 在业务目录（如
op/agents/）创建文件，继承AgentBase或ReActAgent - 实现
run()方法 - 使用
@register_agent注册到AgentRegistry - Prompt 模板放在
op/resources/prompts/<agent_name>/ - 通过
self.load_template()加载模板（基于get_prompt_path()解析路径）
AgentBase 核心 API
load_template(path)→ 从 prompt 根目录加载 Jinja2 模板run()→ Agent 执行入口（子类必须实现）- LLM 调用通过
LLMClient完成
不做什么
- 不要直接修改
AgentBase的核心行为——通过继承扩展 - 不要在此目录放业务 Agent（如 KernelGen）——归
op/agents/ - 不要在此目录放测试——归
tests/ut/
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 · 47 lines · 0 tokens per session scan A d807d4c6de7a
SPEC is an agent published in the GitHub repository mindspore-ai/akg (259 stars, last pushed 22d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 451 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
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
model-compatibility
Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.
kimi
Kimi CLI is Moonshot's coding agent. In CCR it is CLI only and always uses Only opened from CCR.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…