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
 

get-shit-done/workflows/execute-phase.md

@@ -121,6 +121,7 @@ Execute each wave in sequence. Within a wave: parallel if `PARALLELIZATION=true`
        - Plan: {phase_dir}/{plan_file}
        - State: .planning/STATE.md
        - Config: .planning/config.json (if exists)
+       - Project skills: .agents/skills/ (if exists — list skills, read SKILL.md for each, follow relevant rules during implementation)
        </files_to_read>
 
        <success_criteria>

get-shit-done/workflows/plan-phase.md

@@ -123,6 +123,8 @@ IMPORTANT: If CONTEXT.md exists below, it contains user decisions from /gsd:disc
 **Phase requirement IDs (MUST address):** {phase_req_ids}
 **Requirements:** {requirements}
 **Prior decisions:** {decisions}
+
+**Project skills:** Check .agents/skills/ directory (if exists) — read SKILL.md files, research should account for project skill patterns
 </additional_context>
 
 <output>
@@ -200,6 +202,8 @@ IMPORTANT: If context exists below, it contains USER DECISIONS from /gsd:discuss
 
 **Research:** {research_content}
 **Gap Closure (if --gaps):** {verification_content} {uat_content}
+
+**Project skills:** Check .agents/skills/ directory (if exists) — read SKILL.md files, plans should account for project skill rules
 </planning_context>
 
 <downstream_consumer>
@@ -268,6 +272,8 @@ IMPORTANT: Plans MUST honor user decisions. Flag as issue if plans contradict.
 - **Deferred Ideas** = Out of scope — plans must NOT include
 
 {context_content}
+
+**Project skills:** Check .agents/skills/ directory (if exists) — verify plans account for project skill rules
 </verification_context>
 
 <expected_output>

get-shit-done/workflows/quick.md

@@ -99,6 +99,8 @@ Task(
 **Project State:**
 @.planning/STATE.md
 
+**Project skills:** Check .agents/skills/ directory (if exists) — read SKILL.md files, plans should account for project skill rules
+
 </planning_context>
 
 <constraints>
@@ -249,6 +251,7 @@ Execute quick task ${next_num}.
 
 Plan: @${QUICK_DIR}/${next_num}-PLAN.md
 Project state: @.planning/STATE.md
+Project skills: .agents/skills/ (if exists — list skills, read SKILL.md for each, follow relevant rules during implementation)
 
 <constraints>
 - Execute all tasks in the plan