ssqaq/trellis-skills/trellis-continue

Continue Current Task

On each actual user resume turn, the main session invokes the global trellis-setup/scripts/auto_update.py check --background --project-root <root> --invocation-id <unique-user-turn-id>. Reuse the id from trellis-start if it already ran this turn. Read status --project-root <root> and use its skills_source for pinned task skills. Continue working while the check runs. Install only at the safe boundaries defined by the global update rules; after archive and journal, finish-work invokes apply-pending --wait-seconds 15. Delegated agents and progress-only questions do not start update operations.

Resume work on the current task — pick up at the right phase/step in .trellis/workflow.md.

Step 1: Load Current Context

python ./.trellis/scripts/get_context.py

Confirms: current task, git state, recent commits.

Step 2: Load the Phase Index

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

Shows the Phase Index (Plan / Execute / Finish) with routing + skill mapping.

Step 3: Decide Where You Are

get_context.py shows the active task's status field. Route by status + artifact presence. This command replaces the user needing to remember the Trellis flow; it does not itself approve implementation.

• status=planning + no prd.md → 1.1 (load trellis-brainstorm)
• status=planning + prd.md only → decide whether the task is lightweight or complex. Lightweight can move to 1.4 review; complex returns to 1.1 to add design.md + implement.md.
• status=planning + complex artifacts complete + sub-agent jsonl not curated (only the seed _example row) → 1.3
• status=planning + required artifacts complete + required jsonl curated or inline mode → 1.4 (ask for start review; only run task.py start after user confirms)
• status=in_progress + implementation not started → 2.1
• status=in_progress + implementation done, not yet checked → 2.2
• status=in_progress + check passed → 3.3 (spec update) → 3.4 (authorized commit) → 3.5 (trellis-finish-work, automatically in the same turn)
• status=in_progress + implementation/spec updates/authorized commits done → 3.5 directly. Do not wait for completed; normal archive writes that status after the finish gate.
• status=completed (rare; usually archived immediately) → finish flow; invoke trellis-finish-work, whose first step is a fresh full trellis-check before archive

Phase rules (full detail in .trellis/workflow.md):

1. Run steps in order within a phase — [required] steps must not be skipped
2. [once] steps are already done if the required output exists. prd.md alone can be enough only for lightweight tasks; complex tasks also need design.md and implement.md.
3. You may go back to an earlier phase if discoveries require it

Step 4: Load the Specific Step

Once you know which step to resume at:

python ./.trellis/scripts/get_context.py --mode phase --step <X.X> --platform codex

Follow the loaded instructions. After each [required] step completes, move to the next. The main session must not stop after committing or merely remind the user to invoke finish-work. Continue into it when this task's requested work is complete. Delegated agents return their scoped result to the main session; they do not start another task closeout. Respect explicit pause/stop/Trellis opt-out requests.

Reference

Full workflow and detailed phase steps live in .trellis/workflow.md. This command is only an entry point — the canonical guidance is there.