From 6bffcf12be0490575f19a44c7342187bf5887503 Mon Sep 17 00:00:00 2001 From: Lex Christopherson Date: Wed, 14 Jan 2026 16:56:06 -0600 Subject: [PATCH] chore: delete old files --- commands/gsd/_archive/execute-phase.md | 119 ------------------ commands/gsd/status.md | 161 ------------------------- 2 files changed, 280 deletions(-) delete mode 100644 commands/gsd/_archive/execute-phase.md delete mode 100644 commands/gsd/status.md diff --git a/commands/gsd/_archive/execute-phase.md b/commands/gsd/_archive/execute-phase.md deleted file mode 100644 index 804fe1a98..000000000 --- a/commands/gsd/_archive/execute-phase.md +++ /dev/null @@ -1,119 +0,0 @@ ---- -name: gsd:execute-phase -description: Execute all plans in a phase with intelligent parallelization -argument-hint: "" -allowed-tools: - - Read - - Write - - Edit - - Bash - - Glob - - Grep - - Task - - TaskOutput - - AskUserQuestion - - SlashCommand ---- - - -Execute all unexecuted plans in a phase with parallel agent spawning. - -Analyzes plan dependencies to identify independent plans that can run concurrently. -Spawns background agents for parallel execution, each agent commits its own tasks atomically. - -**Critical constraint:** One subagent per plan, always. This is for context isolation, not parallelization. Even strictly sequential plans spawn separate subagents so each starts with fresh 200k context at 0%. - -Use this command when: -- Phase has 2+ unexecuted plans -- Want "walk away, come back to completed work" execution -- Plans have clear dependency boundaries - - - -@~/.claude/get-shit-done/workflows/execute-plan.md -@~/.claude/get-shit-done/workflows/execute-phase.md -@~/.claude/get-shit-done/templates/summary.md -@~/.claude/get-shit-done/references/checkpoints.md -@~/.claude/get-shit-done/references/tdd.md - - - -Phase number: $ARGUMENTS (required) - -@.planning/STATE.md -@.planning/config.json - - - -1. Validate phase exists in roadmap -2. Find all PLAN.md files without matching SUMMARY.md -3. If 0 or 1 plans: suggest /gsd:execute-plan instead -4. If 2+ plans: follow execute-phase.md workflow -5. Monitor parallel agents until completion -6. Present results and next steps - - - -**Strategy A: Fully Autonomous** (no checkpoints) - -- Spawn subagent to execute entire plan -- Subagent creates SUMMARY.md and commits -- Main context: orchestration only (~5% usage) - -**Strategy B: Segmented** (has verify-only checkpoints) - -- Execute in segments between checkpoints -- Subagent for autonomous segments -- Main context for checkpoints -- Aggregate results → SUMMARY → commit - -**Strategy C: Decision-Dependent** (has decision checkpoints) - -- Execute in main context -- Decision outcomes affect subsequent tasks -- Quality maintained through small scope (2-3 tasks per plan) - - - -During execution, handle discoveries automatically: - -1. **Auto-fix bugs** - Fix immediately, document in Summary -2. **Auto-add critical** - Security/correctness gaps, add and document -3. **Auto-fix blockers** - Can't proceed without fix, do it and document -4. **Ask about architectural** - Major structural changes, stop and ask user - -Only rule 4 requires user intervention. - - - -**Per-Task Commits:** - -After each task completes: -1. Stage only files modified by that task -2. Commit with format: `{type}({phase}-{plan}): {task-name}` -3. Types: feat, fix, test, refactor, perf, chore -4. Record commit hash for SUMMARY.md - -**Plan Metadata Commit:** - -After all tasks complete: -1. Stage planning artifacts only: PLAN.md, SUMMARY.md, STATE.md, ROADMAP.md -2. Commit with format: `docs({phase}-{plan}): complete [plan-name] plan` -3. NO code files (already committed per-task) - -**NEVER use:** -- `git add .` -- `git add -A` -- `git add src/` or any broad directory - -**Always stage files individually.** - - - -- [ ] All independent plans executed in parallel -- [ ] Dependent plans executed after dependencies complete -- [ ] Each task committed individually (feat/fix/test/refactor) -- [ ] All SUMMARY.md files created -- [ ] Metadata committed by orchestrator -- [ ] Phase progress updated - diff --git a/commands/gsd/status.md b/commands/gsd/status.md deleted file mode 100644 index 63ffd5755..000000000 --- a/commands/gsd/status.md +++ /dev/null @@ -1,161 +0,0 @@ ---- -name: gsd:status -description: Check status of background agents from parallel execution -argument-hint: "[--wait]" -allowed-tools: - - Read - - Write - - Bash - - TaskOutput ---- - - -Monitor background agent status from /gsd:execute-phase parallel execution. - -Shows running/completed agents from agent-history.json. -Uses TaskOutput to check status of background tasks. -With --wait flag, blocks until all agents complete. - - - -Arguments: $ARGUMENTS - - - - - -**Load agent history:** - -```bash -cat .planning/agent-history.json 2>/dev/null || echo '{"entries":[]}' -``` - -If file doesn't exist or has no entries: -``` -No background agents tracked. - -Run /gsd:execute-phase to spawn parallel agents. -``` -Exit. - - - -**Find background agents:** - -Filter entries where: -- `execution_mode` is "parallel" or "background" -- `status` is "spawned" (still running) or recently completed - -Group by `parallel_group` if present. - - - -**Check status of running agents:** - -For each agent with `status === "spawned"`: - -Use TaskOutput tool: -``` -task_id: [agent_id] -block: false -timeout: 1000 -``` - -**If TaskOutput returns completed result:** -- Update agent-history.json: status → "completed" -- Set completion_timestamp -- Parse files_modified from output if present - -**If TaskOutput returns "still running":** -- Keep as spawned (running) - -**If TaskOutput returns error:** -- Update agent-history.json: status → "failed" - - - -**Show status table:** - -``` -Background Agents -════════════════════════════════════════ - -| Plan | Status | Elapsed | Agent ID | -|--------|-------------|----------|---------------| -| 10-01 | ✓ Complete | 2m 15s | agent_01H... | -| 10-02 | ⏳ Running | 1m 30s | agent_01H... | -| 10-04 | ✓ Complete | 1m 45s | agent_01H... | - -Progress: 2/3 complete - -════════════════════════════════════════ -Wait for all: /gsd:status --wait -``` - -**Status icons:** -- ✓ Complete -- ⏳ Running -- ✗ Failed -- ⏸ Queued (waiting for dependency) - - - -**If --wait flag provided:** - -For each agent with status "spawned": - -Use TaskOutput with blocking: -``` -task_id: [agent_id] -block: true -timeout: 600000 -``` - -Report as each completes: -``` -⏳ Waiting for 3 agents... - -✓ [1/3] 10-01 complete (2m 15s) -✓ [2/3] 10-04 complete (1m 45s) -✓ [3/3] 10-02 complete (3m 30s) - -════════════════════════════════════════ -All agents complete! - -Total time: 3m 30s (parallel) -Sequential estimate: 7m 30s -Time saved: ~4m (53%) -════════════════════════════════════════ -``` - -Update agent-history.json with completion status for each. - - - -**After all complete (or if already complete):** - -``` ---- - -## ▶ Next Up - -All parallel agents finished. Review results: - -`/gsd:progress` - -`/clear` first → fresh context window - ---- -``` - - - - - -- [ ] Reads agent-history.json for background agents -- [ ] Uses TaskOutput to check running agent status -- [ ] Updates history with current status -- [ ] Shows simple status table -- [ ] --wait flag blocks until all complete -- [ ] Reports time savings vs sequential -