$ loading_
Execute implementation plans by splitting and advancing independent tasks in-session.
This skill appears to be prompt-only process documentation with no declared secrets, remote endpoints, or standalone executable component, so the overall risk is low. The main caveat is supply-chain confidence: low community adoption, no declared license, and unknown maintenance status.
The material explicitly states that no keys or environment variables are required. As a prompt-only skill, it does not itself handle credentials, and no signs of credential collection, storage, or misuse are shown.
No remote endpoints are declared, and the documentation does not describe sending user data to external services. Based on the material itself, it does not constitute a network egress capability.
This is a procedural README/prompt describing how to dispatch subagents for tasks, not an installable program, script, or MCP tool interface. Although it mentions implementing, testing, and committing, the material itself does not directly grant code-execution capability.
It does not declare permissions to read or write local files, databases, or other resources. Its 'isolated context' description is methodological only, with no stated data-access scope or overbroad authorization requirement.
The source is an open-source GitHub repository, which is a positive factor for auditability. However, the repo has 0 stars, unknown maintenance status, and no declared license, reducing source trust and governance predictability; manual review of the repository contents and update history is advisable.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "subagent-driven-development" skill from askskill: 1. Download https://raw.githubusercontent.com/obra/superpowers/main/skills/subagent-driven-development/SKILL.md 2. Save it as ~/.claude/skills/subagent-driven-development/SKILL.md 3. Reload skills and tell me it's ready
Based on this implementation plan, split user authentication, payment callbacks, and logging/monitoring into independent tasks, advance them separately, and then summarize the results, risks, and next-step recommendations for each task.
A task-by-task execution summary with progress, issues, and follow-up recommendations for each module.
I have a refactoring plan for a codebase. Split the data layer, API layer, and test additions into independently executable tasks, handle them separately in this session, and provide final integration recommendations.
A refactor progress report by task, including an integration plan and dependency notes.
Please organize and execute these development to-dos as independent tasks: fix the login bug, add unit tests, and update the deployment script. For each, explain completion status, blockers, and priority recommendations.
A per-task status summary and priority assessment to help continue the overall plan.
Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.
Why subagents: You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.
Core principle: Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration
Continuous execution: Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are: BLOCKED status you cannot resolve, ambiguity that genuinely prevents progress, or all tasks complete. "Should I continue?" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it.
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):
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];
"Mark task complete in TodoWrite" [shape=box];
}
"Read plan, extract all tasks with full text, note context, create TodoWrite" [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];
"Read plan, extract all tasks with full text, note context, create TodoWrite" -> "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"];
…
Helps decide merge, PR, or cleanup steps after branch work is complete.
Create, revise, and validate AI skills before deployment.
Systematically investigate bugs, test failures, and unexpected behavior before fixing.
Turn requirements into a clear step-by-step execution plan before implementation.
Set conversation rules to discover and invoke skills before replying.
Clarify intent, requirements, and solution direction before any creative implementation work.
Execute implementation plans with task-specific subagents and code review checkpoints.
Launch parallel autonomous AI agents from one MCP client for complex tasks.
Speed up complex tasks with parallel execution while preserving correctness.
Research, plan, and execute large code changes with parallel PR-producing agents.
Document agent decisions and pass structured context during agent handoffs.
Enable parallel specialized sub-agents and durable logs for Codex CLI workflows.