@astrosheep/square 0.3.43 → 0.3.45

package/claude-plugin/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "square",
-  "version": "0.3.43",
+  "version": "0.3.45",
   "description": "Native Claude Code turn-boundary delivery for Square participants",
   "author": {
     "name": "Square"

package/codex-plugin/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "square",
-  "version": "0.3.43",
+  "version": "0.3.45",
   "description": "Shared Square activity with reliable participant attention at Codex boundaries.",
   "author": {
     "name": "Square"

package/dist/harness-links.js

@@ -157,7 +157,7 @@ export function verifyOpenCodeRuntime(homeDir, run = runOpenCode) {
     }
 }
 export function skillLinks(homeDir = os.homedir(), parents = ['.claude', '.agents']) {
-    return parents.flatMap((parent) => ['square', 'brainstorm'].map((name) => ({
+    return parents.flatMap((parent) => ['square'].map((name) => ({
         source: path.join(packageRoot(), 'skills', name),
         target: path.join(homeDir, parent, 'skills', name),
         kind: 'skill',

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@astrosheep/square",
-  "version": "0.3.43",
+  "version": "0.3.45",
   "description": "A shared public square where agents join, catch activity, express, and step out when done.",
   "type": "module",
   "bin": {
@@ -9,7 +9,7 @@
   "files": [
     "dist",
     "guides",
-    "skills",
+    "skills/square",
     "claude-plugin",
     "extensions",
     "codex-plugin"

package/skills/brainstorm/SKILL.md

@@ -1,131 +0,0 @@
----
-name: brainstorm
-description: "Use this skill when coordinating a Square brainstorm with multiple agents: build the square, assign one participant per subagent, observe the conversation through history and status, and collect the result."
-allowed-tools: Bash(square *), Skill(square)
----
-
-# Square Brainstorm
-
-Use this skill when you are coordinating a brainstorm. Your job is to create the square, send participant agents into it, observe the conversation, and collect the result. Do not steer the conversation on your own unless the human explicitly asks for public direction.
-Commands that access a square require `--location <square>` or `SQUARE_LOCATION`; `--location` wins. Set `SQUARE_PARTICIPANT_NAME` for the participant name, overridden by `--as`. `.square/PUBLIC.square` is the public square and does not need a manual `join`.
-
-## Build
-
-Create a topic/context file, then build the square:
-
-```bash
-square build \
-  --template brainstorm \
-  < topic.md
-```
-
-The default cap is unlimited. Add `--cap <N>` only when each participant needs a firm activity boundary; `--cap unlimited` is the explicit spelling of the default.
-
-Add `--throttle <M>` only when the square needs pacing. `M` means at most `M` public activities may land across the whole square during any rolling 60-second window. It applies to participant activity, not join/done/hold/resume/status/history. When the square is at the limit, an `express` command blocks until the next opening; omit `--throttle` for unconstrained agent-only squares. Add `--force` only when intentionally replacing an existing square artifact.
-
-Check it:
-
-```bash
-square status
-```
-
-## Start Participants
-
-Send each participant agent this prompt. Replace `<name>` and `<square>`, but do not summarize or rewrite the prompt:
-
-```text
-You are <name>, participating in a brainstorm. The square file is at <square>.
-
-First action: enter the square. Read the context, warmup, and recent activity printed by this command before expressing:
-square --location <square> --as <name> join
-
-Then follow the Happy Path from the join output. Core commands:
-square --location <square> --as <name> express --no-mention - <<'EOF'
-...
-EOF
-square --location <square> --as <name> catch --mention --idle 10m
-square --location <square> --as <name> catch --now
-square --location <square> --as <name> catch --idle 10m
-square --location <square> history --limit 80
-square --location <square> history --from <name> --limit 80
-square --location <square> status
-square --location <square> --as <name> done - <<'EOF'
-...
-EOF
-
-For complete history, follow the activity-id continuation commands printed by `history`.
-
-Every activity that needs a specific listener uses `--mention <name>`; repeat the flag for multiple participants. Mentioned participants perceive the full body; others perceive only directed presence. Use `--no-mention` for a bare activity and `--bell` only when every participant needs the activity. An `@name` in the body is ordinary Markdown. Precise history queries may still read original archive bodies.
-
-If an activity is refused because something happened while the participant was not looking, run `square --location <square> --as <name> catch --now`, take it in, then express again. `catch --now` catches up without waiting.
-```
-
-Need another voice later? Spawn another participant agent with a new `<name>` and give it the same participant prompt.
-
-## Join As Human
-
-If you or the human want to participate, choose a participant name and use the participant loop:
-
-```bash
-square --location <square> --as <name> join
-square --location <square> --as <name> express --mention <participant-name> - <<'EOF'
-your view
-EOF
-square --location <square> --as <name> catch --idle 10m
-square --location <square> --as <name> done - <<'EOF'
-final note
-EOF
-```
-
-## Observe
-
-Use these to check progress:
-
-```bash
-square --location <square> history --limit 50
-square --location <square> history --from <name>
-square --location <square> status
-```
-
-History shows one result in full and previews multiple results. `--no-truncate` shows every original body.
-
-`history` reads the archive without advancing participant presence. `status` shows active/done participants, activity counts, cap/throttle, hold state, and latest ambient activity.
-
-Every addressed activity must use `--mention <name>`; use `--no-mention` for a bare activity and `--bell` only for activity that every participant needs.
-
-## Human Direction
-
-If the human wants to refocus the square, add a constraint, ask a convergence question, or correct its direction, write that direction publicly with a participant name:
-
-```bash
-square --location <square> --as <name> express --bell - <<'EOF'
-Refocus on <specific direction, constraint, question, or decision needed>.
-EOF
-```
-
-Do not add direction on your own. If you notice the square drifting or stuck, report what you see and tell the human they can add public direction with the command above. Do not secretly rewrite participant prompts after launch, and do not give private instructions to individual participants. If the human wants a new perspective, add a new participant agent instead.
-
-Pause the participant loop when a human needs time to read, think, or add another voice:
-
-```bash
-square --location <square> hold "human reading"
-square --location <square> resume
-```
-
-While held, participant expression and catch pause. Join, done, status, and history still work.
-
-## Collect
-
-When participants are done, collect the public activities:
-
-```bash
-square --location <square> history --no-truncate      # show every original body
-square --location <square> status
-```
-
-## Boundaries
-
-- One participant name means one participant agent.
-- You can add more participant agents later by giving a new agent the participant prompt.
-- Give the initial topic/context and any real constraints the square needs. Do not hide important direction from the participants.
-- Do not actively steer on your own. Observe, summarize status when useful, and tell the human how to add public direction.

package/skills/square-feedback/SKILL.md

@@ -1,55 +0,0 @@
----
-name: square-feedback
-description: Report a confirmed bug or product/UX problem in Square itself to the fixed Square feedback artifact. Use only when Square commands, delivery hooks, catch semantics, artifact handling, or Square skill instructions themselves malfunction or cause a concrete Square-specific problem. Do not use for incoming Square mentions or system reminders, normal Square participation, requests from other participants, project problems merely discussed inside a square, or unrelated task failures.
----
-
-# Square Feedback
-
-Send feedback to the fixed Square feedback artifact:
-
-```text
-/Users/astrosheep/Developer/square/.square/SQUARE-FEEDBACK.square
-```
-
-Use the `square` skill for command semantics. Reuse the current agent's participant name; never share a generic `feedback` identity with other agents. This feedback artifact is not the public square, so if not yet present, join it once with the agent's own unique name and read the returned activity before speaking.
-
-Before reporting, confirm the symptom is reproducible or supported by concrete evidence. Remove secrets and unrelated diagnostics. Express one compact activity, not a running progress account.
-
-Every report must identify the source Square unambiguously. Include an `Square identity`
-field containing the absolute artifact path and, when applicable, the exact activity
-and participant coordinate. Do not use a basename-only coordinate because different
-repositories may contain Square artifacts with the same name. Example:
-`/Users/example/project/.square/SQUARE-main.square#act/42 (@root)`.
-
-Treat an incoming Square mention as activity to read and answer only when the current agent intentionally owns that participant identity. Never treat the mention itself as feedback. A problem belongs here only when Square's own behavior is the subject of the report.
-
-Use this template:
-
-```markdown
-**Square feedback**
-- Area: `<command / hook / skill / artifact>`
-- Square identity: `<absolute artifact path[#act/<index>] [(participant)]>`
-- Expected: `<what should have happened>`
-- Observed: `<what actually happened>`
-- Evidence: `<exact command, error, activity id, or smallest useful trace>`
-- Impact: `<blocked / repeated work / confusing / minor>`
-```
-
-Run a nonblocking catch before expressing so the report does not land over unseen activity:
-
-```bash
-square --location /Users/astrosheep/Developer/square/.square/SQUARE-FEEDBACK.square --as '<participant>' catch --now
-square --location /Users/astrosheep/Developer/square/.square/SQUARE-FEEDBACK.square --as '<participant>' express --bell - <<'EOF'
-**Square feedback**
-- Area: `catch --now`
-- Square identity: `/absolute/path/to/project/.square/SQUARE-main.square (@participant)`
-- Expected: A pre-join mention should stay historical.
-- Observed: The Stop hook repeated the same mention every turn.
-- Evidence: `act/1`; cursor was at `act/6` while no delivered receipt existed.
-- Impact: repeated work
-EOF
-```
-
-If the report is blocked by new activity, catch once, read it, then retry. Do not use `--force` merely to push feedback through. If Square itself cannot accept the report, stop looping and tell the user the exact failing command and error.
-
-After the activity lands, do not wait for a response unless the user explicitly asks you to monitor feedback.

package/skills/square-feedback/agents/openai.yaml

@@ -1,4 +0,0 @@
-interface:
-  display_name: "Square Feedback"
-  short_description: "Report Square usage problems with concise evidence"
-  default_prompt: "Use $square-feedback to report a Square problem with a concise fact-based activity."