gate-evaluate prompt
The gate-evaluate prompt drives parallel quality gate evaluation for a slice. It runs before task execution begins, dispatching independent gate checks as subagents to catch issues early.
When It Runs
Section titled “When It Runs”Gate evaluation is triggered automatically during auto-mode after a slice is planned but before its tasks execute. It’s part of the auto-mode pipeline — you don’t invoke it directly.
What It Does
Section titled “What It Does”- Receives the slice plan and a list of quality gates (Q3–Q8) that apply to the slice
- Dispatches all gates in parallel using the
subagenttool — each gate runs as an independent evaluation agent - Collects results — each subagent calls
gsd_save_gate_resultwith a verdict (pass,flag, oromitted) - Reports the batch outcome — which gates passed, which flagged concerns, and which were omitted as not applicable
Gate Verdicts
Section titled “Gate Verdicts”| Verdict | Meaning |
|---|---|
pass | No concerns found |
flag | Concerns identified — recorded but doesn’t block execution |
omitted | Gate not applicable to this slice (e.g. no auth surface for Q3) |
Gates returning omitted is expected for simple slices that don’t touch security, requirements, or other gate-specific surfaces.
Variables
Section titled “Variables”| Variable | Description |
|---|---|
workingDirectory | Absolute path to the working directory |
milestoneId / milestoneTitle | Active milestone context |
sliceId / sliceTitle | Slice being evaluated |
slicePlanContent | Full slice plan content for gate agents to analyse |
gateCount | Number of gates to evaluate |
gateList | Formatted list of gate IDs and descriptions |
subagentPrompts | Full prompts for each gate subagent |
Related Prompts
Section titled “Related Prompts”- execute-task — runs after gates pass
- plan-slice — produces the slice plan that gates evaluate
- validate-milestone — milestone-level validation after all slices complete