Kill, interrupt, restart, archive, pin, and garbage-collect agentproto sessions safely — including cleaning up a spawn tree's children. Triggers — "kill this session", "stop the agent", "archive old sessions", "restart a crashed session", "clean up sessions", "garbage collect", "pin this session so it doesn't get…
Manage models, billing profiles, and spend on the agentproto daemon — catalogmodels for runnable routes, authprofilecreate/import/setmodels for named credentials, harness presets, usagerollup for spend estimates. Trigger when asked about models, costs, billing, auth profiles, OpenRouter routing, or how much a session…
Attach a completion policy gate (shell check or judge-agent rubric) to a session or fan-in group so turn-end only passes when the gate is green, then optionally auto-commit pending human ack. Use when the user says "gate this session on tests passing", "attach a policy", "commit only if tests are green", "judge…
Send a follow-up prompt to a live agentproto session, interrupt its in-flight turn, switch its model/effort/posture without restarting, or manage its queued prompts. Use when the user says "tell the agent to also...", "interrupt and redirect it", "switch that session to a cheaper model", "promote/skip that queued…
Read what an agentproto session did — tail its recent output, export the full transcript, get a one-sentence summary, check cost/tokens, or locate a specific message. Use when the user says "what did the agent do", "show me the last output", "export that session", "how much did that session cost", "summarize what…
Run a short, allowlisted shell command on the host synchronously through the agentproto daemon and get stdout/stderr/exit code back as a trackable command session. Trigger phrases include "run this command", "execute pnpm test", "check the command allowlist", "tail the command log", "list recent commands run".
Spawn a new agentproto agent session (claude-code, hermes, ...) with a model, cwd, prompt, and optional MCP tool access. Use when the user says "spawn an agent", "start a session", "launch claude-code on this task", "run hermes in the background", or "kick off a worker". Also covers listing already-running sessions…
Use the agentproto shared task board — taskcreate, taskclaim (CAS with rev), tasklist, and taskupdate to coordinate parallel agents on one board, gate done with verify commands, and hand off work claimably. Trigger when coordinating parallel agents, splitting work across sessions, handing off tasks, or needing…
Open a real PTY terminal session through agentproto to drive interactive TUIs (vim, htop, an interactive CLI wizard, a nested claude TUI) with live keystrokes and byte-buffered output. Trigger phrases include "open a terminal", "start a PTY session", "type into the interactive prompt", "attach a terminal panel", "send…
Send messages out and receive replies into agentproto sessions — transmitmessage with contact binding, inboundwatcherstart to poll sources and spawn/route agents per inbound contact, inbound endpoints for POST /inbound/ webhooks, and Telegram bot wiring. Trigger when asked to send outbound messages, wire a webhook…
Expose a local port publicly via agentproto tunnels — tunnelcreate on cloudflare-quick/cloudflare-named/ngrok, tunnellist to avoid duplicates, remoteenable to publish the MCP gateway bearer-gated. Trigger when asked to share a dev server, tunnel localhost, get a public URL, or expose the agent gateway remotely.
Get notified when a spawned agentproto session finishes WITHOUT blocking your own turn — background a CLI wait with a completion notification, or arm a cron re-ping as a durable fallback that survives daemon restarts. Triggers — "notify me when it's done", "wait in the background", "don't block on this", "durable…
Wait for one or more agentproto sessions to finish a turn (fan-in) without a shell polling loop — multiplex sessionmonitor across children, or take a sessioneventspoll cursor before spawning to stay race-free. Triggers — "wait for these agents to finish", "fan in on my children", "wait until turn-end", "block until…
Run multi-stage session pipelines with agentproto workflows — workflowstart with barrier-gated stages of concurrent steps, sessionRef to reuse earlier output, workflowstatus/cancel/retry, workflowrunfile for AIP-15 WORKFLOW.md, and workflowescalationresolve for human answers. Trigger when asked to pipeline agents, fan…
Route code work to cheap capable models through agentproto instead of expensive Claude. Use when you want hermes sessions on OpenRouter models (glm, deepseek, kimi, qwen) or need to pick the right adapter and auth profile for a low-cost coding worker. Triggers: cheap model, glm, deepseek, kimi, openrouter, hermes…
Route agent-driving tasks to agentproto primitives. Use when you need to spawn a session, send a follow-up prompt, read what an agent did, wait for one or many to finish, kill or clean up, gate completion, run a shell command, or drive an interactive TUI. Triggers: spawn agent, prompt session, read output, wait for…
Stay accountable on a long mission by scheduling a cron boss that re-prompts your own session on a fixed local-time schedule. Trigger for durable check-ins - 'cron a status report', 'wake me on a schedule', 're-prompt my session periodically', 'mission check-in boss'.
Package your agents and workflows as an installable agentproto AIP-53 APP and run it end to end. Trigger for app packaging - 'build an agentproto app', 'bundle my agents', 'install and run an app', 'appinstall my workflow bundle'.
Author an agent pack (company/agency/knowledge) and import it into a guild via the registry, BYO repo, or MCP surface. Trigger for pack work - 'author a company pack', 'import a pack', 'pack init', 'ship capabilities as a pack'.
Spawn a parent agent that spawns and supervises its own sub-agents, forming a two-level tree on the agentproto daemon. Trigger for delegation depth - 'agent that spawns sub-agents', 'two-level agent tree', 'let an agent orchestrate on its own'.
Spawn one worker agent on the agentproto daemon, drive it with a brief and follow-ups to a verified result, then tear it down cleanly. Trigger when delegating a single task - 'spawn an agent', 'delegate this to a worker', 'run an agent to completion', 'drive an agent session'.
Run N parallel worker agents on disjoint file/topic ownership and fan their results into one verified deliverable. Trigger when supervising - 'I am the supervisor', 'spawn parallel workers', 'fan-in several agents', 'decompose this mission and delegate'.
Route missions that outlive your attention — durable waiting, completion gates with retries, scheduled cron check-ins, shared task boards, spend tracking, and cleanup. Use when an agent works longer than one turn or you must not block on it. Triggers: supervise, long-running mission, check-in, non-blocking wait…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: