prjct-cli 2.53.0 → 2.54.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "prjct-cli",
-  "version": "2.53.0",
+  "version": "2.54.0",
   "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

@@ -1,6 +1,6 @@
 # AGENTS.md
 
-AI assistant guidance for **prjct-cli** - context layer for AI coding agents. Works with Claude Code, Gemini CLI, and more.
+AI assistant guidance for **prjct-cli** - context layer for AI coding agents. Works with Claude Code, Codex, Gemini CLI, OpenCode, Qwen Code, Cline, Cursor, Windsurf, and any AGENTS.md-aware runtime.
 
 ## What This Is
 
@@ -10,31 +10,15 @@ AI assistant guidance for **prjct-cli** - context layer for AI coding agents. Wo
 
 ---
 
-## Dynamic Agent Generation
+## Agent Contract
 
-Generate agents during `p. sync` based on analysis:
-
-```javascript
-await generator.generateDynamicAgent('agent-name', {
-  role: 'Role Description',
-  expertise: 'Technologies, versions, tools',
-  responsibilities: 'What they handle'
-})
-```
-
-### Guidelines
-1. Read `analysis/repo-summary.md` first
-2. Create specialists for each major technology
-3. Name descriptively: `go-backend` not `be`
-4. Include versions and frameworks found
-5. Follow project-specific patterns
+Run `prjct <command> --md` and follow the CLI output. Prefer `prjct_*` MCP tools when the active client exposes them.
 
 ## Architecture
 
 **Global**: `~/.prjct-cli/projects/{id}/`
 ```
 prjct.db   # SQLite database (all state)
-context/   # now.md, next.md
 agents/    # domain specialists
 ```
 
@@ -44,21 +28,21 @@ agents/    # domain specialists
 
 | Command | Action |
 |---------|--------|
-| `p. init` | Initialize |
-| `p. sync` | Analyze + generate agents |
-| `p. task X` | Start task |
-| `p. done` | Complete subtask |
-| `p. ship` | Ship feature |
-| `p. next` | Show queue |
+| `prjct init` | Initialize |
+| `prjct sync --md` | Analyze + refresh agent context |
+| `prjct task "X" --md` | Start task |
+| `prjct status done --md` | Complete active task |
+| `prjct ship --md` | Ship feature |
+| `prjct status --md` | Show current task/workflow state |
 
 ## Intent Detection
 
 | Intent | Command |
 |--------|---------|
-| Start task | `p. task` |
-| Finish | `p. done` |
-| Ship | `p. ship` |
-| What's next | `p. next` |
+| Start task | `prjct task "<desc>" --md` |
+| Finish | `prjct status done --md` |
+| Ship | `prjct ship --md` |
+| What's active | `prjct status --md` |
 
 ## Implementation
 

package/templates/antigravity/SKILL.md

@@ -7,16 +7,16 @@ description: Use when user mentions p., prjct, task tracking, or workflow comman
 
 Grammar: `p. <command> [args]` or `prjct <command> --md`
 
-Core commands: sync, task, done, ship, pause, resume, next, bug, workflow, tokens
-Integrations: linear, jira, enrich
+Core commands: sync, task, status, ship, bug, workflow, spec, guard, capture, remember, context
+Integrations: linear, jira
 Other: run `prjct <command> --md` and follow CLI output
 
-Flow: idea → roadmap → next → task → done → ship → next (cycle until plan complete)
+Flow: idea → spec when warranted → task → work → status done → ship
 
 Rules:
 - Persist everything (memories, captures, specs) in ENGLISH, whatever language the user speaks
 - prjct runs → LLM generates relevant data → prjct stores it → LLM requests it from prjct → LLM uses it
 - 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
+- Start code tasks with `prjct task "<desc>" --md` and follow the CLI output
 - Worktree hygiene: if working in a git worktree, remove it AFTER its PR merges — `git worktree remove` from the main worktree; never with uncommitted/unpushed work, never `--force`

package/templates/codex/SKILL.md

@@ -7,10 +7,10 @@ description: Use when the user mentions p., prjct, tasks, specs, shipping, or pr
 
 Run `prjct <command> --md` and follow its output. Pull context on demand; never dump it all.
 
-- Flow: `task` → work → `done` → `ship`
+- Flow: `prjct task` → work → `prjct status done` → `prjct ship`
 - Memory (write in ENGLISH always): `prjct remember <decision|gotcha|learning|fact> "<text>"`, `prjct context memory <topic>` (recall), `prjct guard <file>` (preventive memory before editing)
 - Capture stray thoughts: `prjct capture "<text>"`
 - Worktrees: remove only AFTER the PR merges, from the main worktree; never with unpushed work.
-- Run `prjct --help` for the full command list; prefer the prjct MCP tools (`prjct_*`) when available.
+- `prjct --help` lists commands; prefer prjct MCP tools (`prjct_*`) when available.
 
 Commit footer: `Generated with [p/](https://www.prjct.app/)`

package/templates/cursor/router.mdc

@@ -5,5 +5,5 @@ alwaysApply: true
 
 # prjct
 
-Core: /sync, /task, /done, /ship, /pause, /resume, /next, /bug, /workflow
+Core: /sync, /task, /status, /ship, /bug, /workflow, /spec, /guard
 Other: run `prjct <command> --md` and follow CLI output

package/templates/global/ANTIGRAVITY.md

@@ -1,10 +1,10 @@
 <!-- prjct:start - DO NOT REMOVE THIS MARKER -->
 # p/ — Context layer for AI agents
 
-Skills auto-activate for: task, done, pause, resume, ship, next, sync, bug, workflow, enrich, linear, jira, plan, velocity, tokens
+Skills auto-activate for: task, status, ship, sync, bug, workflow, spec, guard, capture, remember, context, linear, jira
 Other commands: run `prjct <command> --md` and follow CLI output
 
-Flow: idea → roadmap → next → task → done → ship → next (cycle until plan complete)
+Flow: idea → spec when warranted → task → work → status done → ship
 
 Data:
 - prjct runs → LLM generates relevant data → prjct stores it → LLM requests it from prjct → LLM uses it

package/templates/global/CURSOR.mdc

@@ -6,10 +6,10 @@ alwaysApply: true
 <!-- prjct:start - DO NOT REMOVE THIS MARKER -->
 # p/ — Context layer for AI agents
 
-Skills auto-activate for: task, done, pause, resume, ship, next, sync, bug, workflow, enrich, linear, jira, plan, velocity, tokens
+Skills auto-activate for: task, status, ship, sync, bug, workflow, spec, guard, capture, remember, context, linear, jira
 Other commands: run `prjct <command> --md` and follow CLI output
 
-Flow: idea → roadmap → next → task → done → ship → next (cycle until plan complete)
+Flow: idea → spec when warranted → task → work → status done → ship
 
 Data:
 - prjct runs → LLM generates relevant data → prjct stores it → LLM requests it from prjct → LLM uses it

package/templates/global/GEMINI.md

@@ -1,10 +1,10 @@
 <!-- prjct:start - DO NOT REMOVE THIS MARKER -->
 # p/ — Context layer for AI agents
 
-Skills auto-activate for: task, done, pause, resume, ship, next, sync, bug, workflow, enrich, linear, jira, plan, velocity, tokens
+Skills auto-activate for: task, status, ship, sync, bug, workflow, spec, guard, capture, remember, context, linear, jira
 Other commands: run `prjct <command> --md` and follow CLI output
 
-Flow: idea → roadmap → next → task → done → ship → next (cycle until plan complete)
+Flow: idea → spec when warranted → task → work → status done → ship
 
 Data:
 - Persist everything (memories, captures, specs) in ENGLISH, whatever language the user speaks

package/templates/global/STORAGE-SPEC.md

@@ -269,7 +269,7 @@ prjctDb.setDoc(projectId, 'key', data)
 p. task "add feature X"
 
 # Switch to Gemini, continue
-p. done  # Should work seamlessly
+prjct status done --md  # Should work seamlessly
 
 # Switch back to Claude
 p. ship  # Should read Gemini's changes correctly

package/templates/global/WINDSURF.md

@@ -6,10 +6,10 @@ description: "prjct - Context layer for AI coding agents"
 <!-- prjct:start - DO NOT REMOVE THIS MARKER -->
 # p/ — Context layer for AI agents
 
-Skills auto-activate for: task, done, pause, resume, ship, next, sync, bug, workflow, enrich, linear, jira, plan, velocity, tokens
+Skills auto-activate for: task, status, ship, sync, bug, workflow, spec, guard, capture, remember, context, linear, jira
 Other commands: run `prjct <command> --md` and follow CLI output
 
-Flow: idea → roadmap → next → task → done → ship → next (cycle until plan complete)
+Flow: idea → spec when warranted → task → work → status done → ship
 
 Data:
 - prjct runs → LLM generates relevant data → prjct stores it → LLM requests it from prjct → LLM uses it

package/templates/windsurf/router.md

@@ -5,5 +5,5 @@ description: "prjct - Context layer for AI coding agents"
 
 # prjct
 
-Core: /sync, /task, /done, /ship, /pause, /resume, /next, /bug, /workflow
+Core: /sync, /task, /status, /ship, /bug, /workflow, /spec, /guard
 Other: run `prjct <command> --md` and follow CLI output