planning-with-files · galaxy-dawn — Claude Code skill: setup and usage
Stores an agent's working memory in disk files. Helpful for multi-step tasks across multiple tool calls where chat context might degrade.
npx skills add Galaxy-Dawn/claude-scholar --skill planning-with-files -a claude-codeWhat planning-with-files does
The skill implements a three-file workflow: task_plan.md, notes.md, and a final deliverable file. Before tackling complex work, the agent drafts phases with checkboxes and concrete goals. Completed phases get marked right away, and encountered errors are logged directly to disk.
Instead of overloading the transient chat context, research findings go into notes.md. The agent re-reads task_plan.md before making major decisions to keep current goals in its attention window. This structure allows tasks to pause and resume cleanly.
Running this pattern on single-file edits or quick lookups creates unnecessary file churn. Keep it for tasks spanning three or more steps.
What it helps with
- track execution phases in
task_plan.md - offload heavy research findings into
notes.md - log errors and resolutions during multi-step runs
- resume interrupted agent workflows from disk
Example prompts for the agent
- Use planning-with-files to research and implement the new auth flow
- Create task_plan.md and begin phase 1 of the migration
- Update the task plan with our latest benchmark notes
How to install planning-with-files
1Skills CLI (Vercel)
npx skills add Galaxy-Dawn/claude-scholar --skill planning-with-files -a claude-code2Manually: put the files in place
~/.claude/skills/planning-with-files/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/planning-with-files/
1Skills CLI (Vercel)
npx skills add Galaxy-Dawn/claude-scholar --skill planning-with-files -a codex2Manually: put the files in place
.agents/skills/planning-with-files/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Galaxy-Dawn/claude-scholar --skill planning-with-files -a cursor2Manually: put the files in place
.cursor/skills/planning-with-files/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Galaxy-Dawn/claude-scholar planning-with-files2Manually: put the files in place
.github/skills/planning-with-files/SKILL.md1Skills CLI (Vercel)
npx skills add Galaxy-Dawn/claude-scholar --skill planning-with-files -a gemini-cli2Platform CLI
gemini skills install https://github.com/Galaxy-Dawn/claude-scholar --path skills/planning-with-filesManually: put the files in place
.devin/skills/planning-with-files/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add Galaxy-Dawn/claude-scholar --skill planning-with-files -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about planning-with-files
How to install planning-with-files in Claude Code?
Run npx skills add Galaxy-Dawn/claude-scholar --skill planning-with-files -a claude-code. The skill will be placed in ~/.claude/skills/planning-with-files/SKILL.md.
What does planning-with-files do?
It turns markdown files into durable working memory for AI agents. The workflow separates progress tracking, research notes, and outputs into distinct disk files so the model avoids losing context.
When should you skip planning-with-files?
Skip it for single-file edits and quick code lookups. Creating and updating disk files for one-step actions adds unnecessary overhead.
Source text
SKILL.md · MIT
--- name: planning-with-files description: Use this by default for non-trivial multi-step work that needs persistent planning, progress tracking, or durable notes on disk. Trigger when a task will likely span multiple tool calls, research steps, verification loops, or enough context that the plan should not live only in transient chat memory. version: 0.1.0 --- # Planning with Files Work like Manus: use persistent markdown files as your working memory on disk. This is not just an optional planning style. It should be the default persistence layer for complex Codex work. Use it proactively when: - the task will likely take more than a few tool calls - progress needs to be tracked across phases - findings or evidence must be preserved while working - the task may branch, pause, or resume later - relying on chat context alone would be fragile ## Quick Start Before ANY complex task: 1. **Create `task_plan.md`** in the working directory 2. **Define phases** with checkboxes 3. **Update after each phase** - mark [x] and change status 4. **Read before deciding** - refresh goals in attention window ## The 3-File Pattern For every non-trivial task, create THREE files: | File | Purpose | When to Update | |------|---------|----------------| | `task_plan.md` | Track phases and progress | After each phase | | `notes.md` | Store findings and research | During research | | `[deliverable].md` | Final output | At completion | ## Core Workflow ``` Loop 1: Create task_plan.md with goal and phases Loop 2: Research → save to notes.md → update task_plan.md Loop 3: Read notes.md → create deliverable → update task_plan.md Loop 4: Deliver final output ``` ### The Loop in Detail **Before each major action:** ```bash Read task_plan.md # Refresh goals in attention window ``` **After each phase:** ```bash Edit task_plan.md # Mark [x], update status ``` **When storing information:** ```bash Write notes.md # Don't stuff context, store in file ``` ## task_plan.md Template Create this file FIRST for any complex task: ```markdown # Task Plan: [Brief Description] ## Goal [One sentence describing the end state] ## Phases - [ ] Phase 1: Plan and setup - [ ] Phase 2: Research/gather information - [ ] Phase 3: Execute/build - [ ] Phase 4: Review and deliver ## Key Questions 1. [Question to answer] 2. [Question to answer] ## Decisions Made - [Decision]: [Rationale] ## Errors Encountered - [Error]: [Resolution] ## Status **Currently in Phase X** - [What I'm doing now] ``` ## notes.md Template For research and findings: ```markdown # Notes: [Topic] ## Sources ### Source 1: [Name] - URL: [link] - Key points: - [Finding] - [Finding] ## Synthesized Findings ### [Category] - [Finding] - [Finding] ``` ## Critical Rules ### 1. ALWAYS Create Plan First Never start a complex task without `task_plan.md`. This is non-negotiable. ### 2. Read Before Decide Before any major decision, read the plan file. This keeps goals in your attention window. ### 3. Update After Act After completing any phase, immediately update the plan file: - Mark completed phases with [x] - Update the Status section - Log any errors encountered ### 4. Store, Don't Stuff Large outputs go to files, not context. Keep only paths in working memory. ### 5. Log All Errors Every error goes in the "Errors Encountered" section. This builds knowledge for future tasks. ## When to Use This Pattern **Use 3-file pattern for:** - Multi-step tasks (3+ steps) - Research tasks - Building/creating something - Tasks spanning multiple tool calls - Anything requiring organization **Skip for:** - Simple questions - Single-file edits - Quick lookups ## Anti-Patterns to Avoid | Don't | Do Instead | |-------|------------| | Use TodoWrite for persistence | Create `task_plan.md` file | | State goals once and forget | Re-read plan before each decision | | Hide errors and retry | Log errors to plan file | | Stuff everything in context | Store large content in files | | Start executing immediately | Create plan file FIRST | ## Advanced Patterns See [reference.md](reference.md) for: - Attention manipulation techniques - Error recovery patterns - Context optimization from Manus See [examples.md](examples.md) for: - Real task examples - Complex workflow patterns
© Galaxy-Dawn · MIT · Galaxy-Dawn/claude-scholar
Similar skills
All skills for Agent setup: memory, context, orchestration →planning-with-files by other authors comes first.