Subagent Driven Development
Use when executing implementation plans with independent tasks in the current session. Dispatches a fresh subagent per task with two-stage review (spec compliance, then code quality).
Install
$ agentstack add skill-rbraga01-a-team-subagent-driven-development ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Subagent-Driven Development
Execute a plan by dispatching fresh subagents per task, with two-stage review after each.
Core principle: Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration.
Continuous execution: Do not pause to check in between tasks. Execute all tasks without stopping. The only reasons to stop: BLOCKED status you cannot resolve, genuine ambiguity, or all tasks complete.
Process
Step 0: Setup
- Read plan file once; extract ALL tasks with full text and context
- Create TodoWrite with all tasks
- Verify git worktree isolation is configured
Per Task:
- Dispatch implementer subagent with full task text + relevant context
- If implementer asks questions → answer, re-dispatch
- Implementer implements, tests, commits, self-reviews
- Dispatch spec compliance reviewer — confirms code matches spec
- If spec issues → implementer fixes, reviewer re-reviews (loop)
- Dispatch code quality reviewer — confirms quality standards met
- If quality issues → implementer fixes, reviewer re-reviews (loop)
- Mark task complete in TodoWrite
After All Tasks:
- Dispatch final code reviewer for entire implementation
- Use
finishing-a-development-branchskill
Implementer Status Handling
| Status | Action | |--------|--------| | DONE | Proceed to spec compliance review | | DONEWITHCONCERNS | Read concerns, address if correctness/scope issues | | NEEDS_CONTEXT | Provide missing context, re-dispatch | | BLOCKED | Assess: context problem → more context; reasoning → higher model; too large → break up; wrong plan → escalate |
Model Selection
Select the lowest tier that can handle the task:
| Scope | Claude Code | OpenAI | Google | |-------|------------|--------|--------| | 1-2 files, clear spec | claude-haiku-4-5 | gpt-4.1-mini | gemini-2.0-flash-lite | | Multi-file, integration concerns | claude-sonnet-4-6 | gpt-4.1 | gemini-2.5-flash | | Design judgment, broad codebase | claude-opus-4-8 | o3 / gpt-5.5 | gemini-2.5-pro |
Review Order (Critical)
Spec compliance MUST be ✅ before starting code quality review. Never skip either review stage.
Red Flags — Never Do
- Start on main/master branch without explicit user consent
- Skip either review stage
- Dispatch multiple implementation subagents in parallel (file conflicts)
- Make subagent read plan file (provide full text instead)
- Accept "close enough" on spec compliance
- Ignore subagent questions before they start work
Integration
Uses: writing-plans (creates the plan), finishing-a-development-branch (completes work) Subagents use: test-driven-development, code-review patterns
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: RBraga01
- Source: RBraga01/a-team
- License: MIT
- Homepage: https://rbraga01.github.io/a-team/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.