Standup Digest CrewAI
blueprint · 3 agents · 3 MCP servers
1024★ stars
138forks
4.6rating
What it does
A scheduled crew. A collector pulls the issues that moved in the tracker and the pull requests merged in GitHub over the last day. A summarizer groups the activity by person or workstream and condenses it to what's worth saying. A poster drops the digest in the team channel before standup, so the meeting is about blockers, not status. Swap the tracker for your own and run it on a morning schedule.
The cast · 3 agents
Posterposterfast
Post the digest to the team channel as one message with a clear heading for the day. No commentary of your own.
chat.post_message
Collectorcollectorfast
Pull the issues that changed state in the tracker and the pull requests merged in GitHub within the window. Return each with who did it and a one-line what. Read-only.
tracker.list_issuescode.list_commits
Summarizersummarizerreasoning
Group the activity by person or workstream and condense it to what's worth reporting. Drop noise like dependency bumps and formatting. Keep it scannable.
no tools · reasoning only
Flow
→ Collector → activity
→ Summarizer → grouped
→ Poster → digest
Interface
Inputs
windowstring
How far back to look, e.g. 'since yesterday 9am'.
Outputs
digeststring
The standup digest, as posted to Slack.
Depends on · 3 MCP servers
Linearapp.linear/lineartrackerBPublisher
io.github.github/github-mcpnot in the registry yetcode
io.github.slack/slack-mcpnot in the registry yetchat⤓ Export runnable code
# Generated by @socketcat/compiler for target: langgraph
# blueprint: com.socketcat/standup-digest v1.0.0 schema: socketcat.dev/blueprint/v0
# This code is yours. Edit it freely. The socketcat_runtime helper is optional and can be vendored.
from typing import TypedDict
from langgraph.graph import StateGraph, START, END
import socketcat_runtime as _rt
class State(TypedDict, total=False):
window: object
digest: object
activity: object
grouped: object
def node_AgentInvoke_0(state):
return _rt.run_agent("collector", state, {"window":"window"}, "activity")
def node_AgentInvoke_1(state):
return _rt.run_agent("summarizer", state, {"activity":"activity"}, "grouped")
def node_AgentInvoke_2(state):
return _rt.run_agent("poster", state, {"grouped":"grouped"}, "digest")
def build():
b = StateGraph(State)
b.add_node("AgentInvoke_0", node_AgentInvoke_0)
b.add_node("AgentInvoke_1", node_AgentInvoke_1)
b.add_node("AgentInvoke_2", node_AgentInvoke_2)
b.add_edge(START, "AgentInvoke_0")
b.add_edge("AgentInvoke_0", "AgentInvoke_1")
b.add_edge("AgentInvoke_1", "AgentInvoke_2")
b.add_edge("AgentInvoke_2", END)
return b.compile()
INPUTS = ["window"]
OUTPUTS = ["digest"]
if __name__ == "__main__":
_rt.main(build, INPUTS, OUTPUTS)
▸blueprint.json (the portable format)
{
"id": "com.socketcat/standup-digest",
"flow": {
"type": "sequence",
"blocks": [
{
"in": {
"window": "window"
},
"out": "activity",
"use": "collector",
"type": "agent"
},
{
"in": {
"activity": "activity"
},
"out": "grouped",
"use": "summarizer",
"type": "agent"
},
{
"in": {
"grouped": "grouped"
},
"out": "digest",
"use": "poster",
"type": "agent"
}
]
},
"tags": [
"team",
"scheduled",
"reporting",
"sequential"
],
"title": "Standup Digest",
"agents": {
"poster": {
"model": {
"hint": "fast"
},
"title": "Poster",
"tools": [
"chat.post_message"
],
"instructions": "Post the digest to the team channel as one message with a clear heading for the day. No commentary of your own."
},
"collector": {
"model": {
"hint": "fast"
},
"title": "Collector",
"tools": [
"tracker.list_issues",
"code.list_commits"
],
"instructions": "Pull the issues that changed state in the tracker and the pull requests merged in GitHub within the window. Return each with who did it and a one-line what. Read-only."
},
"summarizer": {
"model": {
"hint": "reasoning"
},
"title": "Summarizer",
"instructions": "Group the activity by person or workstream and condense it to what's worth reporting. Drop noise like dependency bumps and formatting. Keep it scannable."
}
},
"estate": {
"grouped": {
"type": "object",
"description": "The activity grouped and condensed by person or workstream."
},
"activity": {
"type": "array",
"description": "The raw tracker and GitHub activity in the window."
}
},
"$schema": "socketcat.dev/blueprint/v0",
"authors": [
{
"url": "https://socketcat.com",
"name": "SocketCat"
}
],
"license": "MIT",
"servers": [
{
"ref": "app.linear/linear",
"alias": "tracker"
},
{
"ref": "io.github.github/github-mcp",
"alias": "code"
},
{
"ref": "io.github.slack/slack-mcp",
"alias": "chat"
}
],
"summary": "Pulls yesterday's tracker and GitHub activity each morning, groups it by person, and posts a standup digest to Slack.",
"targets": [
"crewai",
"langgraph",
"*"
],
"version": "1.0.0",
"interface": {
"inputs": {
"window": {
"type": "string",
"description": "How far back to look, e.g. 'since yesterday 9am'."
}
},
"outputs": {
"digest": {
"type": "string",
"description": "The standup digest, as posted to Slack."
}
}
},
"extensions": {
"com.crewai": {
"process": "sequential"
}
},
"description": "A scheduled crew. A collector pulls the issues that moved in the tracker and the pull requests merged in GitHub over the last day. A summarizer groups the activity by person or workstream and condenses it to what's worth saying. A poster drops the digest in the team channel before standup, so the meeting is about blockers, not status. Swap the tracker for your own and run it on a morning schedule."
}More in Productivity & HR
Browse all →Inbox Chief of Staff
com.socketcat/inbox-chief-of-staff
Custom
Triages your inbox, then routes each thread to the right handler — draft a reply, propose meeting times, or file it — with your approval before anything sends.
★ 14023 servers
⑂ 201