# Subagent Driven Development > Use when executing implementation plans with independent tasks in the current session - Skill: `tomevault-io/subagent-driven-development-36` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add tomevault-io/subagent-driven-development-36` - Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/subagent-driven-development-36/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Coding & Dev Tools - Author: tomevault-io (https://skillmd.com/u/tomevault-io) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/tomevault-io/subagent-driven-development-36 --- # Subagent-Driven Development Execute plan from beads by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review. **Core principle:** Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration **Storage:** Plans tracked in beads epics. No TodoWrite needed - beads provides persistent state. ## When to Use ```dot digraph when_to_use { "Have implementation plan?" [shape=diamond]; "Tasks mostly independent?" [shape=diamond]; "Stay in this session?" [shape=diamond]; "subagent-driven-development" [shape=box]; "executing-plans" [shape=box]; "Manual execution or brainstorm first" [shape=box]; "Have implementation plan?" -> "Tasks mostly independent?" [label="yes"]; "Have implementation plan?" -> "Manual execution or brainstorm first" [label="no"]; "Tasks mostly independent?" -> "Stay in this session?" [label="yes"]; "Tasks mostly independent?" -> "Manual execution or brainstorm first" [label="no - tightly coupled"]; "Stay in this session?" -> "subagent-driven-development" [label="yes"]; "Stay in this session?" -> "executing-plans" [label="no - parallel session"]; } ``` **vs. Executing Plans (parallel session):** - Same session (no context switch) - Fresh subagent per task (no context pollution) - Two-stage review after each task: spec compliance first, then code quality - Faster iteration (no human-in-loop between tasks) ## The Process ```dot digraph process { rankdir=TB; subgraph cluster_per_task { label="Per Task"; "Dispatch implementer subagent (./implementer-prompt.md)" [shape=box]; "Implementer subagent asks questions?" [shape=diamond]; "Answer questions, provide context" [shape=box]; "Implementer subagent implements, tests, commits, self-reviews" [shape=box]; "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" [shape=box]; "Spec reviewer subagent confirms code matches spec?" [shape=diamond]; "Implementer subagent fixes spec gaps" [shape=box]; "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [shape=box]; "Code quality reviewer subagent approves?" [shape=diamond]; "Implementer subagent fixes quality issues" [shape=box]; "Close task in beads (bd close)" [shape=box]; } "Load from beads: bd show , bd ready --parent " [shape=box]; "More tasks remain?" [shape=diamond]; "Dispatch final code reviewer subagent for entire implementation" [shape=box]; "Use superpowers:finishing-a-development-branch" [shape=box style=filled fillcolor=lightgreen]; "Load from beads: bd show , bd ready --parent " -> "Dispatch implementer subagent (./implementer-prompt.md)"; "Dispatch implementer subagent (./implementer-prompt.md)" -> "Implementer subagent asks questions?"; "Implementer subagent asks questions?" -> "Answer questions, provide context" [label="yes"]; "Answer questions, provide context" -> "Dispatch implementer subagent (./implementer-prompt.md)"; "Implementer subagent asks questions?" -> "Implementer subagent implements, tests, commits, self-reviews" [label="no"]; "Implementer subagent implements, tests, commits, self-reviews" -> "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)"; "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" -> "Spec reviewer subagent confirms code matches spec?"; "Spec reviewer subagent confirms code matches spec?" -> "Implementer subagent fixes spec gaps" [label="no"]; "Implementer subagent fixes spec gaps" -> "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" [label="re-review"]; "Spec reviewer subagent confirms code matches spec?" -> "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [label="yes"]; "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" -> "Code quality reviewer subagent approves?"; "Code quality reviewer subagent approves?" -> "Implementer subagent fixes quality issues" [label="no"]; "Implementer subagent fixes quality issues" -> "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [label="re-review"]; "Code quality reviewer subagent approves?" -> "Close task in beads (bd close)" [label="yes"]; "Close task in beads (bd close)" -> "More tasks remain?"; "More tasks remain?" -> "Dispatch implementer subagent (./implementer-prompt.md)" [label="yes"]; "More tasks remain?" -> "Dispatch final code reviewer subagent for entire implementation" [label="no"]; "Dispatch final code reviewer subagent for entire implementation" -> "Use superpowers:finishing-a-development-branch"; } ``` ## Prompt Templates - `./implementer-prompt.md` - Dispatch implementer subagent - `./spec-reviewer-prompt.md` - Dispatch spec compliance reviewer subagent - `./code-quality-reviewer-prompt.md` - Dispatch code quality reviewer subagent ## Example Workflow ``` You: I'm using Subagent-Driven Development to execute this plan. [Load epic from beads: bd show superpowers-abc123] [Get ready tasks: bd ready --parent superpowers-abc123] [Epic has 5 tasks total] Task 1: Hook installation script (superpowers-abc123.1) [Get Task 1 details: bd show superpowers-abc123.1] [Mark in progress: bd update superpowers-abc123.1 --status in_progress] [Dispatch implementation subagent with full task text + context] Implementer: "Before I begin - should the hook be installed at user or system level?" You: "User level (~/.config/superpowers/hooks/)" Implementer: "Got it. Implementing now..." [Later] Implementer: - Implemented install-hook command - Added tests, 5/5 passing - Self-review: Found I missed --force flag, added it - Committed [Dispatch spec compliance reviewer] Spec reviewer: ✅ Spec compliant - all requirements met, nothing extra [Get git SHAs, dispatch code quality reviewer] Code reviewer: Strengths: Good test coverage, clean. Issues: None. Approved. [Close Task 1: bd close superpowers-abc123.1] Task 2: Recovery modes (superpowers-abc123.2) [Get Task 2 details: bd show superpowers-abc123.2] [Mark in progress: bd update superpowers-abc123.2 --status in_progress] [Dispatch implementation subagent with full task text + context] Implementer: [No questions, proceeds] Implementer: - Added verify/repair modes - 8/8 tests passing - Self-review: All good - Committed [Dispatch spec compliance reviewer] Spec reviewer: ❌ Issues: - Missing: Progress reporting (spec says "report every 100 items") - Extra: Added --json flag (not requested) [Implementer fixes issues] Implementer: Removed --json flag, added progress reporting [Spec reviewer reviews again] Spec reviewer: ✅ Spec compliant now [Dispatch code quality reviewer] Code reviewer: Strengths: Solid. Issues (Important): Magic number (100) [Implementer fixes] Implementer: Extracted PROGRESS_INTERVAL constant [Code reviewer reviews again] Code reviewer: ✅ Approved [Close Task 2: bd close superpowers-abc123.2] ... [After all tasks] [Check all closed: bd list --parent superpowers-abc123 --status open] [Empty list - all done] [Dispatch final code-reviewer] Final reviewer: All requirements met, ready to merge [Close epic: bd close superpowers-abc123] [Sync to git: bd sync] Done! ``` ## Advantages **vs. Manual execution:** - Subagents follow TDD naturally - Fresh context per task (no confusion) - Parallel-safe (subagents don't interfere) - Subagent can ask questions (before AND during work) **vs. Executing Plans:** - Same session (no handoff) - Continuous progress (no waiting) - Review checkpoints automatic **Efficiency gains:** - No file reading overhead (controller loads from beads once) - Controller provides full task text to subagents - Subagent gets complete information upfront - Questions surfaced before work begins (not after) - Beads tracks state persistently (survives session restarts) **Quality gates:** - Self-review catches issues before handoff - Two-stage review: spec compliance, then code quality - Review loops ensure fixes actually work - Spec compliance prevents over/under-building - Code quality ensures implementation is well-built **Cost:** - More subagent invocations (implementer + 2 reviewers per task) - Controller does more prep work (extracting all tasks upfront) - Review loops add iterations - But catches issues early (cheaper than debugging later) ## Beads Integration This skill loads plans from beads epics and updates task status during execution. **Initial Setup:** ```bash # Source helper functions source skills/lib/beads-helper.sh # Get epic ID from user or writing-plans output EPIC_ID="superpowers-abc123" # View epic and tasks bd show "$EPIC_ID" bd ready --parent "$EPIC_ID" ``` **Per Task Workflow:** ```bash # Get next ready task TASK_ID=$(bd ready --parent "$EPIC_ID" --format json | jq -r '.[0].id') # Get task details TASK_DESC=$(bd show "$TASK_ID" --json | jq -r '.description') # Mark in progress bd update "$TASK_ID" --status in_progress # [Dispatch implementer subagent with $TASK_DESC] # [Two-stage review process] # [Implementer commits work] # Close task when approved bd close "$TASK_ID" # This automatically unblocks dependent tasks ``` **Key Commands:** - Load epic: `bd show ` - Get ready tasks: `bd ready --parent [--format json]` - Get task details: `bd show [--json]` - Start task: `bd update --status in_progress` - Complete task: `bd close ` - Check progress: `bd list --parent --status open` - Close epic: `bd close ` - Sync to git: `bd sync` **No TodoWrite:** - Beads replaces TodoWrite entirely - All state persists in `.beads/` directory - Synced to git automatically - Survives session restarts and crashes - Dependencies tracked automatically **Passing to Subagents:** - Get task description: `bd show --json | jq -r '.description'` - Pass full description text to implementer subagent - Include context from epic: `bd show ` - Subagents don't need beads access - controller manages state ## Red Flags **Never:** - Start implementation on main/master branch without explicit user consent - Skip reviews (spec compliance OR code quality) - Proceed with unfixed issues - Dispatch multiple implementation subagents in parallel (conflicts) - Make subagent read plan file (provide full text instead) - Skip scene-setting context (subagent needs to understand where task fits) - Ignore subagent questions (answer before letting them proceed) - Accept "close enough" on spec compliance (spec reviewer found issues = not done) - Skip review loops (reviewer found issues = implementer fixes = review again) - Let implementer self-review replace actual review (both are needed) - **Start code quality review before spec compliance is ✅** (wrong order) - Move to next task while either review has open issues **If subagent asks questions:** - Answer clearly and completely - Provide additional context if needed - Don't rush them into implementation **If reviewer finds issues:** - Implementer (same subagent) fixes them - Reviewer reviews again - Repeat until approved - Don't skip the re-review **If subagent fails task:** - Dispatch fix subagent with specific instructions - Don't try to fix manually (context pollution) ## Integration **Required workflow skills:** - **superpowers:using-git-worktrees** - REQUIRED: Set up isolated workspace before starting - **superpowers:writing-plans** - Creates the plan this skill executes - **superpowers:requesting-code-review** - Code review template for reviewer subagents - **superpowers:finishing-a-development-branch** - Complete development after all tasks **Subagents should use:** - **superpowers:test-driven-development** - Subagents follow TDD for each task **Alternative workflow:** - **superpowers:executing-plans** - Use for parallel session instead of same-session execution --- > Converted and distributed by [TomeVault](https://tomevault.io/claim/matthew-reed-holden) — claim your Tome and manage your conversions.