prjct-cli 2.23.10 → 2.23.12

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "prjct-cli",
-  "version": "2.23.10",
+  "version": "2.23.12",
   "description": "Context layer for AI agents. Project context for Claude Code, Gemini CLI, and more.",
   "main": "dist/bin/prjct.mjs",
   "bin": {

package/templates/agents/AGENTS.md

@@ -69,3 +69,15 @@ agents/    # domain specialists
 ## Crew mode (opt-in)
 
 Projects that want a multi-agent workflow can run `prjct crew install` to drop a leader/implementer/reviewer trio into `.claude/agents/`, a project `CHECKPOINTS.md`, and a CLAUDE.md snippet that locks the main session into orchestrator role. Templates live in `templates/crew/`. Uninstall with `prjct crew uninstall`. Strictly opt-in — not invoked by `init`/`sync`.
+
+### Crew roster
+
+Each member has a stable name + color so you can identify who is acting at a glance, in any LLM. Source of truth: `templates/crew/registry.json`.
+
+| Name | Role | Color |
+|---|---|---|
+| Leader | Orchestrator | blue |
+| Implementer | Worker | purple |
+| Reviewer | Strict auditor | pink |
+
+Crew SUBAGENT DISPATCH is Claude Code only (only Claude Code currently exposes an Agent tool that can spawn typed subagents). In Codex / Gemini / Cursor / Windsurf the roster above is informational — the same session plays whichever role the prompt names; identify it explicitly when you reply ("acting as Implementer").

package/templates/codex/SKILL.md

@@ -15,6 +15,8 @@ Flow: idea → roadmap → next → task → done → ship → next (cycle until
 
 Rules:
 - prjct runs → LLM generates relevant data → prjct stores it → LLM requests it from prjct → LLM uses it
+- prjct remembers and shows the path; the agent decides how to execute with its own tools
+- Treat prjct output as signals, not a prescriptive harness
 - All commits include footer: `Generated with [p/](https://www.prjct.app/)`
 - All storage through `prjct` CLI (SQLite internally)
 - Start code tasks with `p. task` and follow Context Contract from CLI output

package/templates/crew/agents/implementer.md

@@ -1,8 +1,9 @@
 ---
 name: implementer
-description: Worker. Implements exactly ONE prjct task end-to-end. Writes code, writes tests, self-verifies. Never approves its own work.
+description: "Implementer (Worker, purple). Implements exactly ONE prjct task end-to-end. Writes code, writes tests, self-verifies. Never approves its own work."
 tools: Read, Write, Edit, Glob, Grep, Bash
 model: opus
+color: purple
 ---
 
 # Implementer

package/templates/crew/agents/leader.md

@@ -1,8 +1,9 @@
 ---
 name: leader
-description: Orchestrator. Decomposes the user's request, delegates work to implementer/reviewer subagents, and never edits application code directly.
+description: "Leader (Orchestrator, blue). Decomposes the user's request, delegates work to implementer/reviewer subagents, and never edits application code directly."
 tools: Read, Glob, Grep, Bash, Agent
 model: haiku
+color: blue
 ---
 
 # Leader (Orchestrator)

package/templates/crew/agents/reviewer.md

@@ -1,8 +1,9 @@
 ---
 name: reviewer
-description: Strict reviewer. Approves or rejects an implementer's work against the project checkpoints and conventions. Never edits code.
+description: "Reviewer (Strict auditor, pink). Approves or rejects an implementer's work against the project checkpoints and conventions. Never edits code."
 tools: Read, Glob, Grep, Bash
 model: sonnet
+color: pink
 ---
 
 # Reviewer

package/templates/crew/registry.json

@@ -0,0 +1,27 @@
+{
+  "$schema": "./registry.schema.json",
+  "version": 1,
+  "crew": [
+    {
+      "id": "leader",
+      "name": "Leader",
+      "role": "Orchestrator",
+      "color": "blue",
+      "summary": "Decomposes the user's request and delegates to implementer/reviewer subagents. Never edits application code."
+    },
+    {
+      "id": "implementer",
+      "name": "Implementer",
+      "role": "Worker",
+      "color": "purple",
+      "summary": "Takes one prjct task from active to ready-for-review. Writes code, writes tests, self-verifies. Never approves its own work."
+    },
+    {
+      "id": "reviewer",
+      "name": "Reviewer",
+      "role": "Strict auditor",
+      "color": "pink",
+      "summary": "Approves or rejects work against project checkpoints and conventions. Never edits code."
+    }
+  ]
+}

package/templates/global/ANTIGRAVITY.md

@@ -8,9 +8,13 @@ Flow: idea → roadmap → next → task → done → ship → next (cycle until
 
 Data:
 - prjct runs → LLM generates relevant data → prjct stores it → LLM requests it from prjct → LLM uses it
+- prjct remembers and shows the path; the agent decides how to execute with its own native tools
+- Treat prjct output as signals, not a prescriptive harness
 - Commit footer: `Generated with [p/](https://www.prjct.app/)`
 - Path resolution: `.prjct/prjct.config.json` → `~/.prjct-cli/projects/{projectId}`
 - Storage: `prjct` CLI (SQLite internally)
 
+Crew (opt-in via `prjct crew install`): Leader (blue) · Implementer (purple) · Reviewer (pink). Subagent dispatch is Claude-Code-only; in Antigravity, identify the role you are playing explicitly.
+
 **Auto-managed by prjct-cli** | https://prjct.app
 <!-- prjct:end - DO NOT REMOVE THIS MARKER -->

package/templates/global/CURSOR.mdc

@@ -13,9 +13,13 @@ Flow: idea → roadmap → next → task → done → ship → next (cycle until
 
 Data:
 - prjct runs → LLM generates relevant data → prjct stores it → LLM requests it from prjct → LLM uses it
+- prjct remembers and shows the path; the agent decides how to execute with its own native tools
+- Treat prjct output as signals, not a prescriptive harness
 - Commit footer: `Generated with [p/](https://www.prjct.app/)`
 - Path resolution: `.prjct/prjct.config.json` → `~/.prjct-cli/projects/{projectId}`
 - Storage: `prjct` CLI (SQLite internally)
 
+Crew (opt-in via `prjct crew install`): Leader (blue) · Implementer (purple) · Reviewer (pink). Subagent dispatch is Claude-Code-only; in Cursor, identify the role you are playing explicitly.
+
 **Auto-managed by prjct-cli** | https://prjct.app
 <!-- prjct:end - DO NOT REMOVE THIS MARKER -->

package/templates/global/GEMINI.md

@@ -8,9 +8,13 @@ Flow: idea → roadmap → next → task → done → ship → next (cycle until
 
 Data:
 - prjct runs → LLM generates relevant data → prjct stores it → LLM requests it from prjct → LLM uses it
+- prjct remembers and shows the path; the agent decides how to execute with its own native tools
+- Treat prjct output as signals, not a prescriptive harness
 - Commit footer: `Generated with [p/](https://www.prjct.app/)`
 - Path resolution: `.prjct/prjct.config.json` → `~/.prjct-cli/projects/{projectId}`
 - Storage: `prjct` CLI (SQLite internally)
 
+Crew (opt-in via `prjct crew install`): Leader (blue) · Implementer (purple) · Reviewer (pink). Subagent dispatch is Claude-Code-only; in Gemini, identify the role you are playing explicitly.
+
 **Auto-managed by prjct-cli** | https://prjct.app
 <!-- prjct:end - DO NOT REMOVE THIS MARKER -->

package/templates/global/WINDSURF.md

@@ -13,9 +13,13 @@ Flow: idea → roadmap → next → task → done → ship → next (cycle until
 
 Data:
 - prjct runs → LLM generates relevant data → prjct stores it → LLM requests it from prjct → LLM uses it
+- prjct remembers and shows the path; the agent decides how to execute with its own native tools
+- Treat prjct output as signals, not a prescriptive harness
 - Commit footer: `Generated with [p/](https://www.prjct.app/)`
 - Path resolution: `.prjct/prjct.config.json` → `~/.prjct-cli/projects/{projectId}`
 - Storage: `prjct` CLI (SQLite internally)
 
+Crew (opt-in via `prjct crew install`): Leader (blue) · Implementer (purple) · Reviewer (pink). Subagent dispatch is Claude-Code-only; in Windsurf, identify the role you are playing explicitly.
+
 **Auto-managed by prjct-cli** | https://prjct.app
 <!-- prjct:end - DO NOT REMOVE THIS MARKER -->

package/templates/skills/prjct/SKILL.md

@@ -1,5 +1,5 @@
 ---
-description: "Project-memory + spec-driven runtime. TRIAGE FIRST, every turn — is this simple or complex? MOST work is SIMPLE (≈1 file, known cause, bug/config/copy/doc, reversible, or the user says fix/hoy/rápido/directo): go DIRECT — `prjct task` → implement → `qa`/`review` → `ship`. NO spec, NO audit-spec, NO reviewer subagents. Spec is the EXCEPTION, ONLY for genuinely complex / high-stakes work (multi-file + new behavior, ambiguous scope, irreversible, or the user frames goals/acceptance/risks): then `spec` → `audit-spec` → `task --spec` → `ship`. Over-routing simple work through spec+reviewers is THE failure mode (burns time/tokens, zero protection on a one-file fix) — when unsure prefer DIRECT and ask one line; never default to spec. Recognize intent in any language (es/en) and run the verb yourself — never make the user type commands. Routine captures (capture/remember/tag) auto-execute, one-line confirm; destructive verbs (ship, status done) suggest-and-confirm; heavy reviews (audit/review/security/investigate) dispatch parallel subagents ONLY when the diff/scope warrants. Lookup-first: vault before re-reading source."
+description: "Project-memory + spec-driven runtime. prjct remembers and shows the path; the agent decides how to execute with its own tools. TRIAGE FIRST, every turn — is this simple or complex? MOST work is SIMPLE (≈1 file, known cause, bug/config/copy/doc, reversible, or the user says fix/hoy/rápido/directo): go DIRECT — `prjct task` → implement → `qa`/`review` → `ship`. NO spec, NO audit-spec, NO reviewer subagents. Spec is the EXCEPTION, ONLY for genuinely complex / high-stakes work (multi-file + new behavior, ambiguous scope, irreversible, or the user frames goals/acceptance/risks): then `spec` → `audit-spec` → `task --spec` → `ship`. Over-routing simple work through spec+reviewers is THE failure mode (burns time/tokens, zero protection on a one-file fix) — when unsure prefer DIRECT and ask one line; never default to spec. Recognize intent in any language (es/en) and run the verb yourself — never make the user type commands. Routine captures (capture/remember/tag) auto-execute, one-line confirm; destructive verbs (ship, status done) suggest-and-confirm; heavy reviews (audit/review/security/investigate) dispatch parallel subagents ONLY when the diff/scope warrants. Lookup-first: vault before re-reading source."
 allowed-tools: ["Bash", "Read", "Write", "Edit", "Glob", "Grep", "Task"]
 user-invocable: true
 ---
@@ -28,6 +28,13 @@ known gotchas). The verb intent map below applies in both states.
 
 
 
+### Agent contract
+
+- prjct remembers project state and shows the path; it does not own the execution.
+- Treat prjct output as durable signals: active task, memories, workflows, specs, risks, and recent learnings.
+- Claude, GPT, and other agents decide the concrete HOW with their own native tools and judgment.
+- Persist meaningful outcomes back through `prjct remember`, `prjct capture`, `prjct task`, and `prjct ship` so the next interaction starts smarter.
+
 ### Primitives
 
 - `prjct spec "<title>"` — frame work BEFORE coding (Goal/Acceptance/Scope/Risks)