Claude Code Workflow Orchestration Framework

Claude Code workflow orchestration framework
95% ai_automation · · 0s · tfww
Do this: This framework stops repeated mistakes across sessions by mandating lessons.md updates after corrections - currently we rely on loose .qa/ practices that lack systematic review triggers.

Comparison to Current State

new value DIFFERENT ANGLE

Current:

New: This reel provides a concrete, structured system prompt framework (CLAUDE.md) for orchestrating AI coding assistants, specifically detailing subagent delegation, autonomous bug fixing, and self-improvement loops, which is not present in the broader AI Web Dev Workflow plan.

new value DIFFERENT ANGLE

Current:

New: While the Cloudflare plan discusses agent infrastructure, this reel introduces a specific, documented protocol for inter-agent communication and task management within a *coding assistant* context, including explicit directives for 'Subagent Strategy' and 'Task Management protocol' that are workflow-level rather than infrastructure-level.

new value DIFFERENT ANGLE

Current:

New: This reel focuses on improving the *quality and efficiency* of individual agent output through structured prompting (e.g., 'Plan Mode Default', 'Self-Improvement Loop'), contrasting with the dashboard/marketplace's focus on managing agents and skills at a higher, abstract level.

Similar to: AI Web Dev Workflow & Premium Animation Tier (0% overlap)
Overlap: AI workflow, developer tools
Different enough to proceed.
Implementing this framework would reduce context window waste, decrease repetition of corrected mistakes across Claude sessions, and enforce staff-engineer quality standards on AI-generated code without increasing engineering overhead.

Implement Boris Cherny's CLAUDE.md framework to formalize self-improvement loops and enforce staff-engineer quality standards through structured prompting.

Business Applications

HIGH claude-upgrades rules consolidation (general)

Merge these 6 workflow sections into ~/.claude/rules/standards.md, specifically adding the '3+ steps' plan mode trigger and the lessons.md self-improvement loop

MEDIUM reelbot agent execution (telegram)

Adopt 'Autonomous Bug Fixing' language into agent_loop.py prompts and add the 6-step Task Management protocol to plan JSON metadata for better audit trails

MEDIUM qa system enhancement (general)

Formalize the .qa/ directory structure to match 'Capture Lessons' workflow - require lessons.md updates after any correction found during review queue processing

LOW claude-dispatcher (general)

Implement 'Subagent Strategy' for complex tasks on VPS2 - use the dispatcher to spawn one-shot subagents for research/exploration while keeping main context clean

Implementation Levels

Tasks

0 selected

Social Media Play

React Angle

We should adopt the 'Self-Improvement Loop' into our existing .qa/ directory structure - we already capture lessons but don't mandate reviewing them at session start, which would prevent repeat mistakes on the ReelBot agent_loop

Repurpose Ideas
Engagement Hook

The '3+ steps = plan mode' rule is chef's kiss. we've been using '2+ files' as our heuristic but step-based is cleaner. what's your trigger for entering plan mode?

What This Video Covers

Boris Cherny appears to be an engineer sharing production-grade Claude Code configuration patterns. The framework reflects senior developer standards and system design principles applied to AI agent management.
Hook: Boris Cherny's CLAUDE.md File
“Enter plan mode for ANY non-trivial task (3+ steps or architectural decisions)”
“Use subagents liberally to keep main context window clean”
“Ruthlessly iterate on these lessons until mistake rate drops”
“Would a staff engineer approve this?”
“If a fix feels hacky: 'Knowing everything I know now, implement the elegant solution”
“Zero context switching required from the user”
“Simplicity First: Make every change as simple as possible”
“No Laziness: Find root causes. No temporary fixes”

Key Insights

Analysis Notes

What it is: A comprehensive CLAUDE.md structure (system prompt/rules file) that enforces strict workflow patterns on Claude Code including mandatory planning, subagent delegation, continuous learning from corrections, and autonomous execution standards.

How it helps us: Directly applicable to our existing 'Claude Upgrades' project. We already have rules consolidation (~1.4k tokens) and context monitoring, but lack the formalized 'Self-Improvement Loop' with lessons.md and the structured Task Management protocol. The 'Autonomous Bug Fixing' section aligns with our QA system but could be formalized.

Limitations: Subagent Strategy requires Claude Code Max plan (which we have but costs 5x per request) - not economical for every task. Some elements may conflict with our existing context-handoff skill at 75% threshold. The 'Verification Before Done' section assumes CI/CD infrastructure not all projects have yet.

Who should see this: Technical leads and developers using Claude Code for production work (Dylan/me). Specifically relevant for the claude-dispatcher project and ReelBot agent_loop.

Cost Breakdown →

StepPromptCompletionCost
analysis19,2822,519$0.0142
similarity1,493600$0.0006
plan11,1334,452$0.0148
Total$0.0296