skills.rest
Syedyasir001
Syedyasir001COMMUNITY
Explore all skills by this author →
GitHub

planning-with-files

Creates and maintains markdown planning files to track multi-step task progress.

Updated Apr 17, 2026
Search Tags:#planning#markdown#context management#agent workflow#task tracking#session recovery#progress logging
One-click install
npx skills add https://github.com/Syedyasir001/RVULibPass --skill planning-with-files-syedyasir001
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: planning-with-files
Source: https://github.com/Syedyasir001/RVULibPass/tree/main/.agent/skills/library/planning-with-files
Command: npx skills add https://github.com/Syedyasir001/RVULibPass --skill planning-with-files-syedyasir001

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires orjson, and includes scripts (resource) components.

What problem does it solve? Long agent sessions lose track of goals after many tool calls because context windows are volatile. This Skill persists plans, findings, and progress to markdown files on disk so work survives context resets and session interruptions. ## Core Features & Use Cases - File-Based Planning: Creates task_plan.md, findings.md, and progress.md in your project directory to track phases, decisions, and errors. - Session Recovery: Detects unsynced context from previous sessions via a catchup script and restores state after /clear. - Lifecycle Hooks: Automatically re-reads the plan before tool calls, reminds you to log progress after edits, and reports phase completion on stop. - Use Case: When asked to research a topic and produce a report requiring many searches and tool calls, the Skill writes each finding to disk immediately, keeping the original goal in the attention window across 50+ tool calls. ## Quick Start Ask the agent to plan out your multi-step project using planning files before starting any work.

Frequently Asked Questions about planning-with-files

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I keep an AI agent on track during long multi-step tasks?▼

Write the plan to a task_plan.md file and re-read it before major decisions. This keeps goals in the model's recent attention window, preventing the 'lost in the middle' effect after many tool calls.

How does file-based planning work with Claude Code hooks?▼

The Skill registers UserPromptSubmit, PreToolUse, PostToolUse, and Stop hooks. These inject the current plan into context before tool calls, prompt progress updates after edits, and report phase completion status when the session stops.

Can I recover task state after clearing the conversation context?▼

Yes. Run the session-catchup.py script, which parses previous session transcripts to find messages after the last planning file update. Then read task_plan.md, progress.md, and findings.md to restore full context.

When should I not use file-based task planning?▼

Skip it for simple questions, single-file edits, and quick lookups. The overhead of creating and maintaining three planning files only pays off for tasks with three or more steps or many tool calls.

Why should web search results not go into task_plan.md?▼

The PreToolUse hook re-reads task_plan.md before every tool call, so untrusted external content there is repeatedly injected into context. Write web results to findings.md instead to reduce prompt injection risk.

Related Skills

Explore More Product & Management Skills→
rafalwizenrafalwizen

research-gatherer

Collect and cross-verify raw research findings from internal and external sources.

Community
Advanced
TomekNoconTomekNocon

implement-spec

Automates end-to-end spec implementation by coordinating subagents.

Community
Advanced
dopsonbrdopsonbr
1

review-implementation

Validate implementation work against plan specifications with Codex CLI reviews.

Community
Intermediate
bamechobamecho
1

planning-with-files

Plan multi-phase tasks using persistent markdown files with session recovery.

Community
Advanced