p

planning-with-files

Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn r

open-sourcecoding-agents
Visit WebsiteView on GitHub
27.2k
Stars
+2267
Stars/month
237
Commits (90d)
10
Releases (6m)

Star Growth

+6.8k (33.3%)estimated from velocity
20.0k23.9k27.7kJul 2Sep 30

Overview

A skill that maintains task_plan.md, findings.md, and progress.md files on disk for AI coding agents. It provides persistent planning that survives context loss, /clear commands, crashes, and compaction through lifecycle hooks that re-inject planning context each turn. It installs across 60+ agents via the Agent Skills standard with native plugins for Claude Code, Codex CLI, and other platforms.

Deep Analysis

Key Differentiator

File-based planning that persists on disk and re-injects every turn, unlike context-window-dependent to-do lists that disappear with memory resets.

⚡ Capabilities

  • • Persistent file-based planning
  • • Session recovery after /clear and crashes
  • • Per-turn context re-injection
  • • Deterministic completion gates
  • • Multi-agent support
  • • Parallel task isolation

🔗 Integrations

Claude CodeCodex CLIPiHermes AgentOpenCodeDeepSeek Harness60+ agents via Agent Skills standard

✓ Best For

  • ✓ Long-running AI coding agent tasks
  • ✓ Projects requiring crash recovery
  • ✓ Maintaining planning context across sessions
  • ✓ Multi-agent coordination

✗ Not Ideal For

  • ✗ End-user AI applications
  • ✗ Non-coding agent workflows
  • ✗ Simple one-off tasks

⚠ Known Limitations

  • ⚠ Requires explicit catchup mode for reading same-project local agent session records
  • ⚠ File-based approach may not suit all workflow preferences

Alternatives

C
Claude-Mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context b
⭐ 95.0k
m
memvid
Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.
⭐ 16.6k
m
memU
Personal memory across agents
⭐ 14.5k
C
Context Mode
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via
⭐ 24.4k
See all 8 planning-with-files alternatives →

Works with planning-with-files

Tools that integrate with planning-with-files, often used together in the same stack.

C
Claude Code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows
h
hermes-agent
The agent that grows with you
D
DeepSeek Harness
DeepSeek Harness: Everything is a Plugin.

Compare planning-with-files

planning-with-files vs Orcaplanning-with-files vs Codexplanning-with-files vs openinterpreterplanning-with-files vs HyperFramesplanning-with-files vs Codewhaleplanning-with-files vs career-ops

Maintain planning-with-files?

Show your live rank in your README, or put planning-with-files in front of every visitor to AgentoolRank.