Overview
Slack is where definitions get argued into existence. Modus mines the channels you select, and every live Slack action can run as the person asking, so an agent never sees a conversation the user could not.
What Modus reads
- 1Workspace
- 2Channel
- 2User
You select the level Modus is allowed to mine. Everything below it is discovered automatically; everything outside it is never touched.
2context types mined
4agent tool groups
1connection method
5security controls
Context types
Each object Modus mines produces typed context items, addressed by their position in the hierarchy. This is what an agent actually receives.
Channel metadata
Selected channels, their purpose and topic, and what the channel is for.
User metadata
Who is who, so an agent can attribute a decision to a person and a team.
Example context item
slack_channel_metadataacme›#data-definitions
- Purpose
- Canonical metric definitions and change requests
- Members
- 84
- Owners
- @dana (Analytics Engineering)
- Signal
- Where "net revenue excludes cancellations" was agreed
Common use cases
- 01
Recover the decision behind a metric from the thread where it was made.
- 02
Let an agent post a governed answer back into the channel that asked.
- 03
Keep an agent strictly inside the channels the requesting user already belongs to.
Connection method
Connect once. Modus stores credentials in a managed secret store, rotates what it can, and never asks an agent to handle them.
OAuth (managed)
Managed OAuth install into your workspace. Scopes are requested once and revocable from Slack.
Security & governance
Governance is applied once, at the layer every agent runs through, so it holds no matter which agent asks.
Metadata-first mining
Modus learns from structure and usage, not bulk data. Raw records stay in your environment; only the metadata needed to understand the system is stored.
Scoped selection
You choose exactly which schemas, folders, spaces, or boards Modus is allowed to see. Nothing outside the selection is ever mined.
Permission mirroring
Tool calls execute as the person asking, not as a shared workspace credential, so an agent can never reach a channel or file the user cannot.
Write approval
Actions that change state in the source system are marked as writes and require an explicit human confirmation before they run.
Group access by sensitivity
Map your identity groups to sensitivity tiers so each team only ever composes context at or below its clearance.
