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 rules/linhai0872/agno-agent-starter/workflowsgit clone --depth 1 https://github.com/linhai0872/agno-agent-starterWhat 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 | $0.00501 |
| Opus 5 | $0.00000 | $0.00251 |
| Sonnet 5 | $0.00000 | $0.00100 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
workflows 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
Workflow 开发规范
何时使用
| 场景 | 推荐方案 |
|---|---|
| 单一任务,工具调用 | Agent |
| 多角色协作,共识决策 | Team |
| 严格步骤控制,条件分支 | Workflow |
目录结构
app/workflows/
├── __init__.py # 注册入口
└── my_workflow.py # Workflow 实现
Workflow 模板
from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.workflow import Workflow
from agno.workflow.step import Step
from agno.workflow.condition import Condition
from app.models import ModelConfig, create_model
WORKFLOW_MODEL_CONFIG = ModelConfig(
model_id="google/gemini-2.5-flash-preview-09-2025",
temperature=0.2,
)
def create_my_workflow(db: PostgresDb) -> Workflow:
researcher = Agent(
name="Researcher",
model=create_model(WORKFLOW_MODEL_CONFIG),
)
writer = Agent(
name="Writer",
model=create_model(WORKFLOW_MODEL_CONFIG),
)
return Workflow(
id="my-workflow",
db=db,
steps=[
Step(name="research", agent=researcher),
Step(name="write", agent=writer),
],
)
条件分支
from agno.workflow.types import StepInput
def needs_review(step_input: StepInput) -> bool:
content = step_input.previous_step_content or ""
return "statistics" in content.lower()
workflow = Workflow(
steps=[
research_step,
Condition(
name="review_condition",
evaluator=needs_review,
steps=[review_step],
),
write_step,
],
)
注册
# app/workflows/__init__.py
from app.workflows.my_workflow import create_my_workflow
workflows.append(create_my_workflow(db))
关键组件
| 组件 | 说明 |
|---|---|
| Step | 单个步骤,包含 Agent 或 Team |
| Condition | 条件分支,evaluator 返回 bool |
| Parallel | 并行执行多个步骤 |
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 · 97 lines · 0 tokens per session scan A 5531612712ae
workflows is a cursor rule published in the GitHub repository linhai0872/agno-agent-starter (6 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 501 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 cursor rules, from other repositories
controlflow-docs-evals
Rules for documentation parity, localized tutorials, and eval verification.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.