mcpField
T
trellis-start

trellis-start

github.com/mindfold-aiAgent workflows15.0k132 installsUpdated 4w ago
Repository

About trellis-start

trellis-start is a session-initialization skill for Trellis-managed development. It gathers project context, workflow guidance, and the next action to help coding agents resume work consistently.

Key features

  1. 01Load session state with get_context.py
  2. 02Review workflow phases and triage rules
  3. 03Find relevant guideline indexes
  4. 04Choose the next task action
  5. 05Route work to related Trellis skills

Use cases

  1. 01Resume a Trellis development session
  2. 02Check an active task's phase and status
  3. 03Find guidance before starting implementation

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/mindfold-ai/trellis --skill trellis-start

After installing, type/trellis-startin Claude Code to confirm it loaded.

Details

From the project README

Start Session

Initialize a Trellis-managed development session. This platform has no session-start hook, so manually load the equivalent compact context by following these steps.

Step 1: Current state

Identity, git status, current task, active tasks, journal location.

python3 ./.trellis/scripts/get_context.py

If this output includes a line beginning Trellis update available:, copy the full line verbatim when summarizing session context. Do not shorten operational command hints.

Step 2: Workflow overview

Compact Phase Index, request triage rules, planning artifact contract, and the step-detail command.

python3 ./.trellis/scripts/get_context.py --mode phase

Full guide in .trellis/workflow.md (read on demand).

Step 3: Guideline indexes

Discover packages + spec layers, then read each relevant index file.

python3 ./.trellis/scripts/get_context.py --mode packages
cat .trellis/spec/guides/index.md
cat .trellis/spec/<package>/<layer>/index.md   # for each relevant layer

Index files list the specific guideline docs to read when you actually start coding.

Step 4: Decide next action

From Step 1 you know the current task and status. Check the task directory:

  • Active task status planning + no prd.md → Phase 1.1. Load the trellis-brainstorm skill.
  • Active task status planning + prd.md exists → stay in Phase 1. Lightweight tasks can be PRD-only; complex tasks need design.md + implement.md. Load the relevant Phase 1 step detail before task.py start.
  • Active task status in_progress → Phase 2 step 2.1. Load the step detail: 
    python3 ./.trellis/scripts/get_context.py --mode phase --step 2.1 --platform codex
  • No active task → classify first. For simple conversation / small task, ask only whether this turn should create a Trellis task. For complex work, ask whether you may create a Trellis task and enter planning. If the user says no, skip Trellis for this session.

Skill routing (quick reference)

User intentSkill
New feature / unclear requirementstrellis-brainstorm
About to write codetrellis-before-dev
Done coding / quality checktrellis-check
Stuck / fixed same bug multiple timestrellis-break-loop
Learned something worth capturingtrellis-update-spec

Full rules + anti-rationalization table in .trellis/workflow.md.

Comments

Markdown supported