A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.
This repository also configures its own agents. See what get-shit-done tells them →
Agent Claude Code
Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /gsd:new-project or /gsd:new-milestone orchestrators.
Agent Claude Code
Synthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by /gsd:new-project after 4 researcher agents complete.
Agent Claude Code
Creates project roadmaps with phase breakdown, requirement mapping, success criteria derivation, and coverage validation. Spawned by /gsd:new-project orchestrator.
Agent Claude Code
Verifies threat mitigations from PLAN.md threat model exist in implemented code. Produces SECURITY.md. Spawned by /gsd:secure-phase.
Agent Claude Code
Retroactive 6-pillar visual audit of implemented frontend code. Produces scored UI-REVIEW.md. Spawned by /gsd:ui-review orchestrator.
Agent Claude Code
Validates UI-SPEC.md design contracts against 6 quality dimensions. Produces BLOCK/FLAG/PASS verdicts. Spawned by /gsd:ui-phase orchestrator.
Agent Claude Code
Produces UI-SPEC.md design contract for frontend phases. Reads upstream artifacts, detects design system state, asks only unanswered questions. Spawned by /gsd:ui-phase orchestrator.
Agent Claude Code
Analyzes extracted session messages across 8 behavioral dimensions to produce a scored developer profile with confidence levels and evidence. Spawned by profile orchestration workflows.
Agent Claude Code
Verifies phase goal achievement through goal-backward analysis. Checks codebase delivers what phase promised, not just that tasks completed. Creates VERIFICATION.md report.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: