AI agent coding-planning / context management
Persistent file-based planning skill for AI coding agents that keeps plan/findings/progress markdown on disk and re-injects them each turn to survive context resets.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Use it when you want a broader self-correcting memory/context-engineering workflow instead of a focused plan-file skill.
Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.
Use it when you want context persistence via ledgers/handoffs specifically for Claude Code.
Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
Use it when you want a visual kanban board to manage coding-agent tasks instead of hidden plan files.
Get 10X more out of Claude Code, Codex or any coding agent
These projects were analysed and named planning-with-files among their alternatives. The relationship is not symmetric — how planning-with-files rates them is a separate judgement, made when planning-with-files is analysed in its own right.
calls planning-with-files “File-based persistent planning to combat context loss; choose if your main issue is planning state, not tool output size.”
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
calls planning-with-files “dedicated crash-proof file-based planning; pick it for long-running tasks where you need persistence beyond Waza's one-off plan”
🥷 Engineering habits you already know, turned into skills Claude can run.