Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
brianlovin avatar

Workflow

  • 10 installs
  • 356 repo stars
  • Updated March 25, 2026
  • brianlovin/agent-config

This is a copy of workflow by brianlovin - installs and ranking accrue to the original listing.

Workflow is a skill that enforces structured execution of complex coding tasks through plan mode, subagent strategy, verification, and a self-improvement loop.

About

Workflow orchestrates complex coding tasks by enforcing structured execution. It defaults to plan mode for any non-trivial task, uses subagents to keep context clean, and requires verification before marking work done. It also runs a self-improvement loop that records corrections in tasks/lessons.md. A developer uses it to impose discipline on multi-step implementations, refactors, and bug fixes.

  • Enforces plan mode for any task with 3+ steps or architectural decisions
  • Prescribes subagent offloading, verification-before-done, and a lessons.md self-improvement loop
  • Tracks work in tasks/todo.md and tasks/lessons.md

Workflow by the numbers

  • 10 all-time installs (skills.sh)
  • Data as of Aug 1, 2026 (Skillselion catalog sync)
At a glance

workflow capabilities & compatibility

Capabilities
planning · code review
Use cases
planning · orchestration
From the docs

What workflow says it does

Enter plan mode for ANY non-trivial task (3+ steps or architectural decisions)
SKILL.md
Use subagents liberally to keep main context window clean
SKILL.md
Never mark a task complete without proving it works
SKILL.md
npx skills add https://github.com/brianlovin/agent-config --skill workflow

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs10
repo stars356
Last updatedMarch 25, 2026
Repositorybrianlovin/agent-config

What it does

Impose structured planning, subagent use, and verification on any non-trivial multi-step coding task.

Who is it for?

Developers wanting disciplined planning and verification on multi-step tasks

Skip if: Simple, obvious one-line fixes that do not need planning

When should I use this skill?

You start a multi-step implementation, refactor, architectural change, or bug fix

What you get

A planned, verified task tracked in todo.md with lessons recorded

  • tasks/todo.md plan
  • tasks/lessons.md updates

By the numbers

  • 6 workflow rules (plan mode through autonomous bug fixing)
  • 6-step task management sequence

Files

SKILL.mdMarkdownGitHub ↗

Workflow Orchestration

1. Plan Mode Default

  • Enter plan mode for ANY non-trivial task (3+ steps or architectural decisions)
  • If something goes sideways, STOP and re-plan immediately — don't keep pushing
  • Use plan mode for verification steps, not just building
  • Write detailed specs upfront to reduce ambiguity

2. Subagent Strategy

  • Use subagents liberally to keep main context window clean
  • Offload research, exploration, and parallel analysis to subagents
  • For complex problems, throw more compute at it via subagents
  • One task per subagent for focused execution

3. Self-Improvement Loop

  • After ANY correction from the user: update tasks/lessons.md with the pattern
  • Write rules for yourself that prevent the same mistake
  • Ruthlessly iterate on these lessons until mistake rate drops
  • Review lessons at session start for relevant project

4. Verification Before Done

  • Never mark a task complete without proving it works
  • Diff behavior between main and your changes when relevant
  • Ask yourself: "Would a staff engineer approve this?"
  • Run tests, check logs, demonstrate correctness

5. Demand Elegance (Balanced)

  • For non-trivial changes: pause and ask "is there a more elegant way?"
  • If a fix feels hacky: "Knowing everything I know now, implement the elegant solution"
  • Skip this for simple, obvious fixes — don't over-engineer
  • Challenge your own work before presenting it

6. Autonomous Bug Fixing

  • When given a bug report: just fix it. Don't ask for hand-holding
  • Point at logs, errors, failing tests — then resolve them
  • Zero context switching required from the user
  • Go fix failing CI tests without being told how

Task Management

1. Plan First: Write plan to tasks/todo.md with checkable items 2. Verify Plan: Check in before starting implementation 3. Track Progress: Mark items complete as you go 4. Explain Changes: High-level summary at each step 5. Document Results: Add review section to tasks/todo.md 6. Capture Lessons: Update tasks/lessons.md after corrections

Core Principles

  • Simplicity First: Make every change as simple as possible. Impact minimal code.
  • No Laziness: Find root causes. No temporary fixes. Senior developer standards.
  • Minimal Impact: Changes should only touch what's necessary. Avoid introducing bugs.

Related skills

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.