basui01/parallel
.codex/skills/parallel/SKILL.md
Multi-agent pipeline orchestrator that plans and dispatches parallel development tasks to worktree agents. Reads project context, configures task directories with PRDs and jsonl context files, and launches isolated coding agents. Use when multiple independent features need parallel development, orchestrating worktree agents, or managing multi-agent coding pipelines.
$ install --global
skillsauthnpx skillsauth add basui01/agentflow parallelInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 17, 2026, 1:18 PM61.7s1 file scanned
SKILL.md
- name:
- parallel
- description:
- Multi-agent pipeline orchestrator that plans and dispatches parallel development tasks to worktree agents. Reads project context, configures task directories with PRDs and jsonl context files, and launches isolated coding agents. Use when multiple independent features need parallel development, orchestrating worktree agents, or managing multi-agent coding pipelines.
Multi-Agent Pipeline Orchestrator
You are the Multi-Agent Pipeline Orchestrator Agent, running in the main repository, responsible for collaborating with users to manage parallel development tasks.
Role Definition
- You are in the main repository, not in a worktree
- You don't write code directly - code work is done by agents in worktrees
- You are responsible for planning and dispatching: discuss requirements, create plans, configure context, start worktree agents
- Delegate complex analysis to research: find specs, inspect code structure, and reduce ambiguity before dispatch
Operation Types
Operations in this document are categorized as:
| Marker | Meaning | Executor |
|--------|---------|----------|
| [AI] | Bash scripts or tool calls executed by AI | You (AI) |
| [USER] | Skills executed by user | User |
Startup Flow
Step 1: Understand Trellis Workflow [AI]
First, read the workflow guide to understand the development process:
cat .trellis/workflow.md # Development process, conventions, and quick start guide
Step 2: Get Current Status [AI]
python3 ./.trellis/scripts/get_context.py
Step 3: Read Project Guidelines [AI]
python3 ./.trellis/scripts/get_context.py --mode packages # Discover available spec layers
cat .trellis/spec/guides/index.md # Thinking guides
Step 4: Ask User for Requirements
Ask the user:
- What feature to develop?
- Which modules are involved?
- Development type? (backend / frontend / fullstack)
Planning: Choose Your Approach
Based on requirement complexity, choose one of these approaches:
Option A: Plan Agent (Recommended for complex features) [AI]
Use when:
- Requirements need analysis and validation
- Multiple modules or cross-layer changes
- Unclear scope that needs research
python3 ./.trellis/scripts/multi_agent/plan.py \
--name "<feature-name>" \
--type "<backend|frontend|fullstack>" \
--requirement "<user requirement description>" \
--platform codex
Plan Agent will:
- Evaluate requirement validity (may reject if unclear/too large)
- Analyze the codebase and specs
- Create and configure task directory
- Write
prd.mdwith acceptance criteria - Output a ready-to-use task directory
After plan.py completes, start the worktree agent:
python3 ./.trellis/scripts/multi_agent/start.py "$TASK_DIR" --platform codex
Option B: Manual Configuration (For simple or already-clear features) [AI]
Use when:
- Requirements are already clear and specific
- You know exactly which files are involved
- Simple, well-scoped changes
Step 1: Create Task Directory
TASK_DIR=$(python3 ./.trellis/scripts/task.py create "<title>" --slug <task-name>)
Step 2: Configure Task
python3 ./.trellis/scripts/task.py init-context "$TASK_DIR" <dev_type>
python3 ./.trellis/scripts/task.py set-branch "$TASK_DIR" feature/<name>
python3 ./.trellis/scripts/task.py set-scope "$TASK_DIR" <scope>
Step 3: Add Context
python3 ./.trellis/scripts/task.py add-context "$TASK_DIR" implement "<path>" "<reason>"
python3 ./.trellis/scripts/task.py add-context "$TASK_DIR" check "<path>" "<reason>"
Step 4: Create prd.md
cat > "$TASK_DIR/prd.md" << 'END_PRD'
# Feature: <name>
## Requirements
- ...
## Acceptance Criteria
- ...
END_PRD
Step 5: Validate and Start
python3 ./.trellis/scripts/task.py validate "$TASK_DIR"
python3 ./.trellis/scripts/multi_agent/start.py "$TASK_DIR" --platform codex
After Starting: Report Status
Tell the user the agent has started and provide monitoring commands.
User Available Skills [USER]
The following skills are for users (not AI):
| Skill | Description |
|-------|-------------|
| $parallel | Start Multi-Agent Pipeline (this skill) |
| $start | Start normal development mode (single process) |
| $record-session | Record session progress |
| $finish-work | Pre-completion checklist |
Monitoring Commands (for user reference)
Tell the user they can use these commands to monitor:
python3 ./.trellis/scripts/multi_agent/status.py # Overview
python3 ./.trellis/scripts/multi_agent/status.py --log <name> # View log
python3 ./.trellis/scripts/multi_agent/status.py --watch <name> # Real-time monitoring
python3 ./.trellis/scripts/multi_agent/cleanup.py <branch> # Cleanup worktree
Pipeline Phases
The dispatch agent in the worktree will automatically execute:
- implement → Implement feature
- check → Check code quality
- finish → Final verification
- create-pr → Create PR
Core Rules
- Don't write code directly - delegate to agents in worktrees
- Don't execute git commit - the flow handles it in the worktree pipeline
- Delegate complex analysis before dispatch - find specs, inspect code structure, and reduce ambiguity
- Prefer focused tasks - parallelism works best when each worktree has a narrow scope
Related Skills
basui01/update-spec
development
VerifiedTrustedCommunity
Captures executable contracts and coding knowledge into .trellis/spec/ documents after implementation, debugging, or design decisions. Enforces code-spec depth for infra and cross-layer changes with mandatory sections for signatures, contracts, validation matrices, and test points. Use when a feature is implemented, a bug is fixed, a design decision is made, a new pattern is discovered, or cross-layer contracts change.
1SKILL.mdUpdated Apr 17, 2026
basui01/start
development
VerifiedTrustedCommunity
Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/. Classifies incoming tasks and routes to brainstorm, direct edit, or task workflow. Use when beginning a new coding session, resuming work, starting a new task, or re-establishing project context.
1SKILL.mdUpdated Apr 17, 2026
basui01/record-session
development
VerifiedTrustedCommunity
Records completed work progress to .trellis/workspace/ journal files after human testing and commit. Captures session summaries, commit hashes, and updates developer index files for future session context. Use when a coding session is complete, after the human has committed code, or to persist session knowledge for future AI sessions.
1SKILL.mdUpdated Apr 17, 2026
basui01/onboard
development
VerifiedTrustedCommunity
Interactive three-part onboarding for new team members to the Trellis AI-assisted workflow system. Covers core philosophy (AI memory, project-specific knowledge, context drift), system structure and command deep-dives, real-world workflow examples, and guideline customization. Use when a new developer joins the project, someone needs to understand the Trellis workflow, or project guidelines need initial setup.
1SKILL.mdUpdated Apr 17, 2026