fix(#672): add project skill discovery to subagent spawn points

Subagents now discover and read .agents/skills/ directory:
- Workflows: execute-phase, plan-phase, quick
- Agents: gsd-executor, gsd-planner, gsd-phase-researcher, gsd-plan-checker

Agents read SKILL.md (lightweight index) and load rules/*.md as needed,
avoiding full AGENTS.md files (100KB+ context cost).

Fixes: #672

Co-Authored-By: Claude <noreply@anthropic.com>

agents/gsd-executor.md

@@ -13,6 +13,19 @@ Spawned by `/gsd:execute-phase` orchestrator.
 Your job: Execute the plan completely, commit each task, create SUMMARY.md, update STATE.md.
 </role>
 
+<project_context>
+Before executing, discover project context:
+
+**Project skills:** Check `.agents/skills/` directory if it exists:
+1. List available skills (subdirectories)
+2. Read `SKILL.md` for each skill (lightweight index ~130 lines)
+3. Load specific `rules/*.md` files as needed during implementation
+4. Do NOT load full `AGENTS.md` files (100KB+ context cost)
+5. Follow skill rules relevant to your current task
+
+This ensures project-specific patterns, conventions, and best practices are applied during execution.
+</project_context>
+
 <execution_flow>
 
 <step name="load_project_state" priority="first">

agents/gsd-phase-researcher.md

@@ -18,6 +18,19 @@ Spawned by `/gsd:plan-phase` (integrated) or `/gsd:research-phase` (standalone).
 - Return structured result to orchestrator
 </role>
 
+<project_context>
+Before researching, discover project context:
+
+**Project skills:** Check `.agents/skills/` directory if it exists:
+1. List available skills (subdirectories)
+2. Read `SKILL.md` for each skill (lightweight index ~130 lines)
+3. Load specific `rules/*.md` files as needed during research
+4. Do NOT load full `AGENTS.md` files (100KB+ context cost)
+5. Research should account for project skill patterns
+
+This ensures research aligns with project-specific conventions and libraries.
+</project_context>
+
 <upstream_input>
 **CONTEXT.md** (if exists) — User decisions from `/gsd:discuss-phase`
 

agents/gsd-plan-checker.md

@@ -23,6 +23,19 @@ Goal-backward verification of PLANS before execution. Start from what the phase
 You are NOT the executor or verifier — you verify plans WILL work before execution burns context.
 </role>
 
+<project_context>
+Before verifying, discover project context:
+
+**Project skills:** Check `.agents/skills/` directory if it exists:
+1. List available skills (subdirectories)
+2. Read `SKILL.md` for each skill (lightweight index ~130 lines)
+3. Load specific `rules/*.md` files as needed during verification
+4. Do NOT load full `AGENTS.md` files (100KB+ context cost)
+5. Verify plans account for project skill patterns
+
+This ensures verification checks that plans follow project-specific conventions.
+</project_context>
+
 <upstream_input>
 **CONTEXT.md** (if exists) — User decisions from `/gsd:discuss-phase`
 

agents/gsd-planner.md

@@ -25,6 +25,19 @@ Your job: Produce PLAN.md files that Claude executors can implement without inte
 - Return structured results to orchestrator
 </role>
 
+<project_context>
+Before planning, discover project context:
+
+**Project skills:** Check `.agents/skills/` directory if it exists:
+1. List available skills (subdirectories)
+2. Read `SKILL.md` for each skill (lightweight index ~130 lines)
+3. Load specific `rules/*.md` files as needed during planning
+4. Do NOT load full `AGENTS.md` files (100KB+ context cost)
+5. Ensure plans account for project skill patterns and conventions
+
+This ensures task actions reference the correct patterns and libraries for this project.
+</project_context>
+
 <context_fidelity>
 ## CRITICAL: User Decision Fidelity