diff --git a/.claude/agents/action-planning-agent.md b/.claude/agents/action-planning-agent.md index c0604ab0..642d836f 100644 --- a/.claude/agents/action-planning-agent.md +++ b/.claude/agents/action-planning-agent.md @@ -42,7 +42,7 @@ You are a pure execution agent specialized in creating actionable implementation ``` **Analysis CLI Usage Standards**: -- **Gemini CLI**: Use task-specific paths: `gemini-wrapper -p "$(.claude/scripts/read-task-paths.sh [task-json-file]) @{CLAUDE.md}" ` +- **Gemini CLI**: Use task-specific paths: `~/.claude/scripts/gemini-wrapper -p "$(.claude/scripts/read-task-paths.sh [task-json-file]) @{CLAUDE.md}" ` - **Codex CLI**: Use task-specific paths: `codex --full-auto exec "$(.claude/scripts/read-task-paths.sh [task-json-file]) [prompt]"` - **Follow Guidelines**: @~/.claude/workflows/gemini-unified.md and @~/.claude/workflows/codex-unified.md diff --git a/.claude/agents/code-developer.md b/.claude/agents/code-developer.md index 16c4deac..16d06e7b 100644 --- a/.claude/agents/code-developer.md +++ b/.claude/agents/code-developer.md @@ -56,7 +56,7 @@ ELIF context insufficient OR task has analysis marker: - **Purpose**: Enables autonomous development with intelligent file discovery and code generation **Analysis CLI Usage Standards**: -- **Gemini CLI**: Use task-specific paths from JSON: `gemini-wrapper -p "$(~/.claude/scripts/read-task-paths.sh [task-json-file]) [prompt]" ` +- **Gemini CLI**: Use task-specific paths from JSON: `~/.claude/scripts/gemini-wrapper -p "$(~/.claude/scripts/read-task-paths.sh [task-json-file]) [prompt]" ` - **Codex CLI**: Use task-specific paths from JSON: `codex --full-auto exec "$(~/.claude/scripts/read-task-paths.sh [task-json-file]) [prompt]"` - **Follow Guidelines**: @~/.claude/workflows/gemini-unified.md and @~/.claude/workflows/codex-unified.md diff --git a/.claude/agents/code-review-test-agent.md b/.claude/agents/code-review-test-agent.md index d231d3c8..10a937a4 100644 --- a/.claude/agents/code-review-test-agent.md +++ b/.claude/agents/code-review-test-agent.md @@ -78,7 +78,7 @@ Use the targeted review context template: **Gemini CLI Command**: ```bash -gemini-wrapper -p "$(.claude/scripts/read-task-paths.sh [task-json-file]) @{CLAUDE.md} [review-analysis-prompt]" +~/.claude/scripts/gemini-wrapper -p "$(.claude/scripts/read-task-paths.sh [task-json-file]) @{CLAUDE.md} [review-analysis-prompt]" ``` This executes a change-specific Gemini CLI command that identifies: diff --git a/.claude/agents/conceptual-planning-agent.md b/.claude/agents/conceptual-planning-agent.md index 3bb709f3..81fec306 100644 --- a/.claude/agents/conceptual-planning-agent.md +++ b/.claude/agents/conceptual-planning-agent.md @@ -53,7 +53,7 @@ def handle_analysis_markers(prompt): if "[GEMINI_CLI_REQUIRED]" in prompt: for dimension in dimensions: result = execute_gemini_cli( - command=f"gemini-wrapper -p \"$(.claude/scripts/read-task-paths.sh [task-json-file]) @{{CLAUDE.md}} {dimension}\"", + command=f"~/.claude/scripts/gemini-wrapper -p \"$(.claude/scripts/read-task-paths.sh [task-json-file]) @{{CLAUDE.md}} {dimension}\"", dimension=dimension, role_context=role, topic=topic diff --git a/.claude/workflows/gemini-unified.md b/.claude/workflows/gemini-unified.md index aba75c0e..034395ce 100644 --- a/.claude/workflows/gemini-unified.md +++ b/.claude/workflows/gemini-unified.md @@ -29,8 +29,9 @@ type: technical-guideline - **Task Detection**: - **Analysis keywords**: "analyze", "analysis", "review", "understand", "inspect", "examine" → `--approval-mode default` - **All other tasks**: → `--approval-mode yolo` -- **Usage**: Identical to `gemini` command - all parameters pass through unchanged +- **Usage**: Use full path `~/.claude/scripts/gemini-wrapper` - all parameters pass through unchanged - **Benefits**: Prevents token limits, optimizes approval workflow, provides error tracking +- **Setup**: Script auto-installs to `~/.claude/scripts/` location ### ⚙️ Command Syntax & Arguments @@ -111,31 +112,31 @@ These are recommended command templates for common scenarios. - **Automatic Token & Approval Management** ```bash # Analysis task - auto adds --approval-mode default - gemini-wrapper -p "Analyze authentication module patterns and implementation" + ~/.claude/scripts/gemini-wrapper -p "Analyze authentication module patterns and implementation" # Execution task - auto adds --approval-mode yolo - gemini-wrapper -p "Implement user login feature with JWT tokens" + ~/.claude/scripts/gemini-wrapper -p "Implement user login feature with JWT tokens" # Navigate to specific directory with wrapper - cd src/auth && gemini-wrapper -p "Review authentication patterns" + cd src/auth && ~/.claude/scripts/gemini-wrapper -p "Review authentication patterns" # Override token threshold if needed - GEMINI_TOKEN_LIMIT=500000 gemini-wrapper -p "Custom threshold analysis" + GEMINI_TOKEN_LIMIT=500000 ~/.claude/scripts/gemini-wrapper -p "Custom threshold analysis" # Multi-directory support with wrapper - gemini-wrapper --include-directories /path/to/other/project -p "Cross-project analysis" + ~/.claude/scripts/gemini-wrapper --include-directories /path/to/other/project -p "Cross-project analysis" ``` - **Module-Specific Analysis (Quick Module Analysis)** ```bash # Navigate to module directory for focused analysis - cd src/auth && gemini-wrapper -p "Analyze authentication module patterns and implementation" + cd src/auth && ~/.claude/scripts/gemini-wrapper -p "Analyze authentication module patterns and implementation" # Or specify module from root directory - cd backend/services && gemini-wrapper -p "Review service architecture and dependencies" + cd backend/services && ~/.claude/scripts/gemini-wrapper -p "Review service architecture and dependencies" # Template-enhanced module analysis with wrapper - cd frontend/components && gemini-wrapper -p "$(cat ~/.claude/workflows/cli-templates/prompts/analysis/pattern.txt)" + cd frontend/components && ~/.claude/scripts/gemini-wrapper -p "$(cat ~/.claude/workflows/cli-templates/prompts/analysis/pattern.txt)" ``` #### 📝 Direct Gemini Usage (Manual Control)