agentleFS
LL4nc33LL4nc33/code-workspace-engine/skills/multi-terminal/SKILL.md

multi-terminal

Skill0 starsChanged 7 months agoMITView on GitHub

Multi-Terminal Parallel Development reference. Handoff protocol, entry format, routing, and coordination patterns for parallel terminal workflows.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Always commit + push: after writing a handoff entry

    line 65
  2. Distinctive:

    Update status: when starting work on a handoff item

    line 67

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Multi-Terminal Parallel Development

Reference skill for coordinating work across multiple Claude Code terminals using git worktrees and structured handoff files.

Architecture

projekt/
├── .trees/
│   ├── t1-*/              # Git Worktrees (one per terminal)
│   ├── t2-*/
│   └── t3-*/
├── shared/
│   └── handoff/
│       ├── README.md       # Protocol explanation
│       ├── *.md            # Handoff files per role pair
│       └── .changelog      # Audit trail
├── terminal-prompts/
│   ├── T1-*.md            # Role + CWE-Agents + First Actions
│   ├── T2-*.md
│   └── T3-*.md

Branch Naming Convention

Worktree branches follow the pattern t{N}-{role}:

  • t1-frontend
  • t2-backend
  • t3-qa

The t\d+- prefix is used by hooks to detect multi-terminal context.

Handoff Protocol

Entry Format

## [YYYY-MM-DD HH:MM] T{source} → T{target}: {title}

**Status:** 📋 TODO | 🔄 IN PROGRESS | ✅ DONE | ❌ BLOCKED | ⚠️ NEEDS REVIEW

**Kontext:** {was gemacht wurde}

**Action Required:** {was der Empfänger tun soll}

---

Status Flow

📋 TODO → 🔄 IN PROGRESS → ✅ DONE
                          → ❌ BLOCKED (with reason)
                          → ⚠️ NEEDS REVIEW

Rules

  1. Always commit + push after writing a handoff entry
  2. Check handoffs first at the start of each work cycle
  3. Update status when starting work on a handoff item
  4. Never delete entries — only update status
  5. One action per entry — keep handoffs atomic

Merge Strategy

Entry-count based: The branch with more entries in a handoff file is considered more complete. During sync, entries from other branches are appended if they don't already exist (matched by timestamp + title).

Presets

PresetTerminalsRoles
A (2T)2Dev + QA
B (3T)3Frontend + Backend + QA
C (4T)4Frontend + Backend + Infra + QA
DCustomUser-defined roles

CWE Agent Mapping

Each terminal role maps to preferred CWE agents:

RolePrimary AgentsSecondary
Frontendbuilder, qualityarchitect, explainer
Backendbuilder, devopsarchitect, security
QAquality, securityresearcher, ask
Infradevops, securityarchitect, researcher
Dev (generic)builder, qualityarchitect, devops

Commands

CommandPurposeWho
/cwe:autopilotAutonomous task loopAny terminal
/cwe:coordinateTeam-lead coordinationTeam Lead (T1)
/cwe:check-handoffRead + summarize handoffsAny terminal
/cwe:handoffWrite handoff entryAny terminal
/cwe:qa-mergeQA-verified merge to mainQA terminal only

Hooks

EventHookPurpose
UserPromptSubmithandoff-sync.pySync entries from other branches
SessionStartmt-session-init.pyDetect worktree + load handoff context

Both hooks silently skip when not in a multi-terminal worktree (no t\d+- branch prefix).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.