inbox
Every platform's chats as one inbox: listing, reading and watching them, sending, reacting and voice notes, who waits on a reply, claiming a chat before acting in it, and every action's log.
Load next, when the work needs it: getGuide({ topic: "voiceGate" }) (The voice gate every send as the owner passes on every platform: a draft checked against the owner's own writing before it goes out, and the voice and AI-tells indexes behind it).
Written by bun run docs:build from the code, the skills and AGENTS.md. Not edited by hand: change the command's usage, its skill or the rule, and rebuild.
Use cases these tools are part of
When the owner asks for one of these, follow its page step by step.
| Use case | What it is | How the owner asks for it |
|---|---|---|
getGuide({ useCase: "discord/channelReply" }) | Answering someone in a Discord DM or group DM | "reply to <someone> on discord", "reply to <someone> in <group>", "explain what I'm trying to do to <someone> in <group>", "answer the group" |
getGuide({ useCase: "discord/serverReply" }) | Replying in a Discord server channel | "reply to <someone> in <server>", "answer him in the general", "message the guy in <server> #<channel> who mentioned me", "reply in the <server> server", "find what <someone> said in <server> and answer it" |
getGuide({ useCase: "inbox/bossMaxxing" }) | Bossmaxxing: giving out tasks to the team | "bossmaxxing", "give out the tasks", "send <person> the task in <group> and tag them", "tell <person> about everything I researched and give them an outline", "triage the jobs across the team", "walk <person> through setting up <tool>", "help <person> get set up like we did with <other person>" |
getGuide({ useCase: "inbox/ignoreServer" }) | Ignoring a server or a chat | "ignore that server", "mute that channel", "stop the alerts from there", "unignore it" |
getGuide({ useCase: "inbox/labelQueue" }) | Teaching log who your people are | "what should i label", "teach the labeller", "train the labeller", "which chats are you unsure about" |
getGuide({ useCase: "inbox/outcomes" }) | Do people answer what log sends? | "do people reply to what log sends", "are log's messages working", "which plays get answers" |
getGuide({ useCase: "inbox/quietPush" }) | Quieting the live push | "go silent for 30 minutes", "turn the notifications back on" |
getGuide({ useCase: "inbox/reaLooksmaxxing" }) | /rea-looksmaxxing: moneymaxx like a creator | "/rea-looksmaxxing how clavicular gets paid", "moneymaxx like <creator>", "how does <creator> get paid" |
getGuide({ useCase: "inbox/reactions" }) | Reacting to a message | "react to that", "heart his message", "put a 😂 on what she said", "send a reaction to <person>" |
getGuide({ useCase: "inbox/scopeAJob" }) | Scoping a job out of someone in a DM | "probe <person> so we can scope out what the task is", "scope it out with him", "find out what he actually wants done", "go through and then scope it out". |
getGuide({ useCase: "inbox/triage" }) | Triage: scoping someone's job and handing it to whoever does it | "triage this", "scope it out with him and pass it to <person>", "inform <person> of what the job is and what he needs to do", "we've already scoped the work with the client, hand it over", "this is a triage job", "don't tell him anyone else is doing it" |
getGuide({ useCase: "inbox/voiceNote" }) | Sending a voice note | "send <person> a voice note saying …", "voice note him that …", "send a vn to the group saying …" |
getGuide({ useCase: "inbox/warmPeople" }) | Working the warm people in your dms | "who's warm", "who can i ask now", "label my people", "who have we been warming up", "mark him as a friend" |
getGuide({ useCase: "twitter/dmInbox" }) | Reading the DM inbox: who is waiting on you | "who is waiting on me", "check my x dms", "go through my twitter inbox and tell me who needs a reply", "who am I waiting on in my dms". |
The tools in this guide
Each tool's own description carries its full usage, notes, live line and rules; logGet gives its exact inputs and a call that works.
| Tool | What it does | Usage |
|---|---|---|
inboxClaim | Claim a chat for this session before drafting or sending in it, so no… | log inbox claim --platform <twitter|discord|slack|instagram> --account <a> --chat <conversationId|handle> [--event <eventId>] [--json] |
inboxRelease | Release this session's claim on a chat when it is done with it | log inbox release --platform <p> --account <a> --chat <conversationId|handle> [--json] |
inboxResume | The owner's go-ahead after a refused catch-up | log inbox resume --platform <p> --account <a> --by <who> [--json] |
inboxWaiting | The people waiting on my reply, counts per platform | log inbox waiting [--platform <p>] [--account <a>] [--limit <n>] [--tail <n>] [--oldest] [--json] |
inboxPending | What the account watchers heard since this reader last asked, with… | log inbox pending --reader <name> [--json] |
inboxQuiet | Quiet the live push for n minutes | log inbox quiet --minutes <n> --by <who> [--json] |
inboxIgnore | Stop pushing a server or a chat to the owner | log inbox ignore --platform <p> (--server <id> | --chat <id>) --by <who> [--undo] [--json] |
inboxIgnored | Every server and chat the push ignores, and who asked | log inbox ignored [--json] |
inboxLabels | Every person in the owner's dms | log inbox labels [--label <l>] [--who <w>] [--where <s>] [--platform <p>] [--account <a>] [--limit <n>] [--json] |
inboxLabel | Set the label on one person's dm by hand, over what log.db says | log inbox label --platform <p> --account <a> --chat <id> (--who <w> [--where <s>] | --as <l>) --by <who> [--undo] [--json] |
inboxLabelQueue | Chats to label first | log inbox label queue [--platform <p>] [--limit <n>] |
inboxLabelTeach | SubQ labels unlabelled chats once | log inbox label teach [--platform <p>] [--limit <n>] [--apply] |
inboxLabelTrain | Train the who and where head on the labels | log inbox label train |
inboxOutcomes | Reply rates of log's sends vs the owner's, matched by person and stage | log inbox outcomes [--platform <p>] [--account <a>] [--feelings] [--json] |
inboxClaims | Every live claim | log inbox claims [--json] |
inboxActions | The log of every claim, refusal, send and release, oldest first, to… | log inbox actions [--platform <p>] [--account <a>] [--chat <conversationId|handle>] [--limit <n>] [--json] |
chatsList | List an account's chats on its own platform, the platform taken from… | log chats list --account <account> [--space <space>] [--limit <limit>] [--platform <p>] [--json] |
messagesRead | Read one chat's messages on the account's own platform, the platform… | log messages read --account <account> --chat <chat> [--space <space>] [--limit <limit>] [--platform <p>] [--json] |
messagesWatch | Listen to an account's messages for a set time as its platform pushes… | log messages watch --account <account> [--chat <chat>] [--space <space>] [--seconds <seconds>] [--platform <p>] [--json] |
messagesSend | Send a message as the account on its own platform, the platform taken… | log messages send --account <account> --chat <chat> --text <text> [--space <space>] [--asOne] [--brief] [--overGate] [--approvedBy <approvedBy>] [--platform <p>] [--live] [--json] |
messagesSendLive | Send a message as the account on its own platform…, live on the platform | log messages send --account <account> --chat <chat> --text <text> [--space <space>] [--asOne] [--brief] [--overGate] [--approvedBy <approvedBy>] [--platform <p>] [--live] [--json] |
messagesReact | React to one message as the account on its own platform, the platform… | log messages react --account <account> --chat <chat> --message <message> --emoji <emoji> [--space <space>] [--approvedBy <approvedBy>] [--platform <p>] [--live] [--json] |
messagesReactLive | React to one message as the account on its own…, live on the platform | log messages react --account <account> --chat <chat> --message <message> --emoji <emoji> [--space <space>] [--approvedBy <approvedBy>] [--platform <p>] [--live] [--json] |
watchersStatus | Each account watcher's state, read from log.db | log watchers status [--platform <p>] [--account <a>] [--json] |
watchersStart | Start the watcher of every signed-in account that isn't running… | log watchers start [--platform <p>] [--account <a>] [--json] |
watchersStop | Stop the named account watchers and hold them until start names them… | log watchers stop [--platform <p>] [--account <a>] [--json] |
voiceNotesSend | Send a voice note in the owner's cloned voice as the account on its… | log voiceNotes send --account <account> --chat <chat> --text <text> [--space <space>] [--approvedBy <approvedBy>] [--platform <p>] [--live] [--json] |
voiceNotesSendLive | Send a voice note in the owner's cloned voice as the…, live on the platform | log voiceNotes send --account <account> --chat <chat> --text <text> [--space <space>] [--approvedBy <approvedBy>] [--platform <p>] [--live] [--json] |
The rules these tools fall under
Each by its number and first line. The full text is in AGENTS.md (log://agents); the core rules are in full in getGuide({ topic: "logMcpInstructions" }).
- Rule 8. Platform actions require the user authorization their tool defines.
- Rule 30. Complete the authorized task.
- Rule 38. Do not introduce discussions of Meta/Facebook rules, terms, eligibility or account ownership unless The owner raises them.
- Rule 39. Use only the scope, options and intent The owner stated or implied.
- Rule 40. Do not propose physical infrastructure unless The owner asks.
- Rule 41. Paid work must stay within the authorized task and spend.
- Rule 89. Find conversational context by scoped search and existing private records.
- Rule 94. Every platform call goes through Log and its governor, never a scratch client with account tokens/cookies.
- Rule 105. One platform/account owns one continuous engine session and push connection.
- Rule 109. Read the full relevant chat and current private context before drafting or sending.
- Rule 123. Platforms use their existing push/watch path to keep private records current.
- Rule 133. Claim a chat before acting; consult recent actions, preserve claim generation and check it before subsequent message parts.
- Rule 134. Existing workspace log.db is the native private record/coordination foundation.
- Rule 137. Preserve current context-aware voice and AI-artifact gates for messages sent as The owner.
- Rule 138. Media and voice-note context uses the existing private media descriptions and transcripts.
- Rule 142. Send a cloned voice note only when The owner asks, through the platform's native voice-note tool and existing provider adapter.
- Rule 154. Show people/chats by meaningful names and handles; keep routing ids internal unless needed for the specific technical artifact.
- Rule 160. Answer eligible chat reads from log.db when the owner is live, caught up and the needed history is present/backfilled.
- Rule 163. Agent Log actions go through Log MCP tools; never work around a stale or unavailable MCP with shell Log commands or scratch clients.