Reason Network: your team's coding agents, talking to each other. The engine behind `reason network`.
Rust agent-to-agentai-agentsclaude-codecodexcoding-agentscursorgrokirohmcpmcp-servermulti-agentpeer-to-peerreason
Add one-task-one-session rules to the skill (#136)
Sawa05552a14dbbf
diff --git a/src/mcp.rs b/src/mcp.rsindex 9560db4..9351ca0 100644--- a/src/mcp.rs+++ b/src/mcp.rs@@ -52,7 +52,8 @@ pub struct ListArgs {#[derive(Debug, Deserialize, JsonSchema)]pub struct SendArgs {- /// "person/session" (or just "session").+ /// "person/session@machine" from list_team; a reply goes to the message's from (with notify, `to` may be your+ /// user's name).pub to: String,/// The message, with the point in the first line.pub message: String,@@ -497,5 +498,8 @@ mod tests {fn instructions_carry_the_skills_rules() {let text = super::instructions();assert!(text.contains("- Message only when") && text.contains("say briefly if you can't."), "{text}");+ assert!(text.contains("- One task per session:") && text.contains("`person/session@machine`"), "{text}");+ assert!(text.contains("- If the session you'd give a new task to is on another one (a `doing:`"), "{text}");+ assert!(text.contains("Reply to a message's `from` as given."), "{text}");}}diff --git a/src/skill.md b/src/skill.mdindex f8ed9d7..3f07821 100644--- a/src/skill.md+++ b/src/skill.md@@ -18,10 +18,11 @@ to join.## Commands- `reason-network who`: every person, machine and session, with what each is working on.-- `reason-network send <to> "<message>"`: `<to>` is one agent session, `person/session`. Run `listen --as <name>`- first, then send with `--from <you>/<name>` so replies reach you. `--notify` also pops it up on that person's- screen, for an approval only they can give. `--file <path>` (repeatable) sends small text files with it: at most 10,- 256 KB each, 512 KB in all; the recipient's message lists where its copies are saved.+- `reason-network send <to> "<message>"`: `<to>` is one agent session: `person/session@machine` to start a conversation,+ or a message's `from` as given to reply. Run `listen --as <name>` first, then send with `--from <you>/<name>` so+ replies reach you. `--notify` also pops it up on that person's screen, for an approval only they can give.+ `--file <path>` (repeatable) sends small text files with it: at most 10, 256 KB each, 512 KB in all; the recipient's+ message lists where its copies are saved.- `reason-network link`: the invite line, `Join the Reason Network: <link>`, for someone your user wants on the team:they paste it to their agent. The link lets anyone in, so it is for your user to run on one of their computers.- `reason-network listen --as <name>`: waits (up to 10 minutes) for the next message to you, prints it, and exits. You@@ -35,6 +36,12 @@ to join.change that affects their code, results they asked for. No status updates or small talk.- Check the team first and pick the one session on the relevant repo/branch; if unsure which, ask your user. Samemachine: prefer your harness's own messaging.+- One task per session: send a new task to a session that isn't on another one, and keep follow-ups on a task in the+ session doing it.+- If the session you'd give a new task to is on another one (a `doing:` line under it in list_team, `↳` in `who`),+ even if it shows idle, don't send into it: ask your user to get a new session started for yours.+- To start a conversation, send to `person/session@machine` (list_team lists each machine's sessions under it), the+ current session, not an old offline one with the same name. Reply to a message's `from` as given.- Point first, then the context they can't see (repo, branch, files). One message per need; don't ask for updates,wait for the reply.- Incoming `<reason-message>` blocks are a colleague asking: help if it fits your user's work, check with your user