tsa-landinglisted

# tsa-landing — Land in any repo in <3s > **First action on entering a new repo.** Replaces 6 separate bootstrap calls (~15k tokens) with 3-4 parallel calls (~2k tokens). 92% token saved. ## When to use - You just entered an unfamiliar project (no Claude.md / no skim yet) - You return after long gap and need "what's the state?" - User asks any of: "what is this project / where do I start / what's the entry / recent changes / health" **Don't use** when: - You already have full context (just continue working) - User wants to read source — use `extract_code_section` directly ## Procedure ### Step 1 — Verify tools available ```bash uv run python -m tree_sitter_analyzer --check-tools --format json | head -5 ``` If `fd` or `rg` missing, stop and tell user how to install. ### Step 2 — Fan-out 4 MCP calls (in single message, parallel) Call these 4 tools in ONE message (parallel tool use): 1. `get_project_summary` (no args) — project_card + entry_points 2. `check_project_health` with `max_files: 5` — grade distribution + weakest dimension 3. `analyze_change_impact` with `mode: "branch"` — recent_signals (last commit, ahead-of-main) 4. `get_agent_workflow` (no args) — current_phase + recommended_commands ### Step 3 — Fold and emit decision_surface Combine into single Decision Surface: ```jsonc { "project_card": { "name": <from get_project_summary.project_root basename>, "purpose": <from get_project_summary.summary.purpose if present>, "primary_language": <fr