Agent skill

Planning With Files

by Galaxy-Dawn in Galaxy-Dawn/claude-scholar

Keeps a long task on track by writing a plan, running notes and the final deliverable to markdown files on disk instead of relying on chat memory.

MITAuto-check passedAgent Workflows

Install Planning With Files

skills CLI
$ npx skills add Galaxy-Dawn/claude-scholar --skill planning-with-files -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Galaxy-Dawn/claude-scholar planning-with-files --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Galaxy-Dawn/claude-scholar.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/planning-with-files .claude/skills/planning-with-files && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
planning-with-files
GitHub stars
5.7k
Token cost
~1.1k tokens
SKILL.md length
387 words
Files
3
Skills in repo
34
Repo updated
First seen
Licence
MIT

At a glance

Keeps a long task on track by writing a plan, running notes and the final deliverable to markdown files on disk instead of relying on chat memory.

  • Works in 5 steps: ALWAYS Create Plan First → Read Before Decide → Update After Act → …
  • Starting a research task that will need many searches and a written result
  • SKILL.md covers Quick Start, The 3-File Pattern, Core Workflow and task_plan.md Template, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

This skill makes plain markdown files the agent's working memory for any task likely to take many tool calls, span phases, branch, pause or resume. It uses three files: task_plan.md holds the goal, phases with checkboxes and a status section; notes.md stores findings and research; and a separate deliverable file receives the final output.

The loop is simple. The agent reads the plan before each major action so the goal stays in view, marks the phase done and updates the status afterward, and writes large outputs into the notes file rather than keeping them in context, holding only file paths. Its listed rules are to create the plan first, read before deciding, update after acting, store rather than stuff, and log errors; the excerpt is cut off in the last of these. Templates for both files and two extra files, examples.md and reference.md, come with it.

When your agent uses it

  • Starting a research task that will need many searches and a written result
  • Working through a multi-phase change where progress must survive a pause or restart
  • Keeping evidence and decisions in notes instead of long chat context

Example prompts

  • “Plan this migration in task_plan.md first, then work through it phase by phase.”
  • “Research three vector database options, keep findings in notes.md and write the comparison to a separate file.”
  • “Pick up where we left off by reading task_plan.md and tell me which phase is next.”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. ALWAYS Create Plan First
  2. Read Before Decide
  3. Update After Act
  4. Store, Don't Stuff
  5. Log All Errors

What it can do on your machine

Read from SKILL.md and the folder at commit 9037873. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Planning With Files loads about 1.1k tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 387 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~80
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Galaxy-Dawn/claude-scholar at commit 9037873, republished under its MIT licence (© Galaxy-Dawn). 387 words, ~1,071 tokens.

Download SKILL.mdSave it as .claude/skills/planning-with-files/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
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:

FilePurposeWhen to Update
task_plan.mdTrack phases and progressAfter each phase
notes.mdStore findings and researchDuring research
[deliverable].mdFinal outputAt 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.

Show full SKILL.md (166 more words)Show less
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'tDo Instead
Use TodoWrite for persistenceCreate task_plan.md file
State goals once and forgetRe-read plan before each decision
Hide errors and retryLog errors to plan file
Stuff everything in contextStore large content in files
Start executing immediatelyCreate plan file FIRST

Advanced Patterns

See reference.md for:

  • Attention manipulation techniques
  • Error recovery patterns
  • Context optimization from Manus

See examples.md for:

  • Real task examples
  • Complex workflow patterns

© Galaxy-Dawn, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in skills/planning-with-files of Galaxy-Dawn/claude-scholar.

  • SKILL.md
  • examples.md
  • reference.md

Open the folder on GitHubat commit 9037873

Compare with similar skills

Planning With Files next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Planning With Files compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Planning With Files this skillGalaxy-Dawn/claude-scholar5.7k—~1.1kAutomated safety check: PassMIT
MemPalace Recall for Planningopen-gsd/gsd-core10k1 repos~1.5kAutomated safety check: NotesMIT
Planning with FilesOthmanAdi/planning-with-files27k—~2.9kAutomated safety check: PassMIT
Planning With FilesOthmanAdi/planning-with-files27k—~3kAutomated safety check: PassMIT
Planning with Files for KiroOthmanAdi/planning-with-files27k—~2.1kAutomated safety check: PassMIT
File-Based Planning in ArabicOthmanAdi/planning-with-files27k—~3.2kAutomated safety check: NotesMIT

Similar skills

  • Recalls earlier decisions, patterns and surprises from MemPalace memory before planning, behind a config gate that never blocks the planning step.

    10k GitHub starsUsed in 1 repo~1.5k tokens
    Agent WorkflowsAuto-check: notes
  • Planning with Files

    OthmanAdi/planning-with-files

    Keeps a task plan, findings and progress log in markdown files on disk so long agent tasks survive context resets, with Gemini hooks and helper scripts.

    27k GitHub stars~2.9k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed
  • Planning With Files

    OthmanAdi/planning-with-files

    Keeps a task plan, findings and progress log as Markdown files in the project so long multi-step agent work survives context resets.

    27k GitHub stars~3k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed
  • Planning with Files for Kiro

    OthmanAdi/planning-with-files

    Keeps task_plan.md, findings.md and progress.md on disk as the agent's working memory for multi-step work, wired into Kiro steering, with no hooks.

    27k GitHub stars~2.1k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed
  • File-Based Planning in Arabic

    OthmanAdi/planning-with-files

    Arabic edition of a file-based planning skill that keeps task_plan.md, findings.md and progress.md on disk so multi-step agent work survives lost context.

    27k GitHub stars~3.2k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check: notes
  • File-Based Planning in Spanish

    OthmanAdi/planning-with-files

    Spanish edition of a planning skill that keeps a multi-step agent task on track with task_plan.md, findings.md and progress.md on disk, with recovery after a session reset.

    27k GitHub stars~3.8k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check: notes

More from Galaxy-Dawn/claude-scholar

All 34 skills in this repo
  • Citation Verification Guide

    Galaxy-Dawn/claude-scholar

    Reference guidance for checking every citation in academic writing against canonical sources such as DOI, arXiv, CrossRef and Semantic Scholar, to catch fake or wrong references.

    5.7k GitHub starsUsed in 2 repos~1.9k tokens
    Auto-check passed
  • Skill Improvement Plan Executor

    Galaxy-Dawn/claude-scholar

    Reads an improvement-plan file from a companion quality-review skill and applies its suggested fixes to a Claude Skill, backing up first.

    5.7k GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed
  • Skill Quality Reviewer

    Galaxy-Dawn/claude-scholar

    Scores a skill across description, content organization, writing style and structure, then produces letter grades and a prioritized improvement plan.

    5.7k GitHub starsUsed in 1 repo~3k tokens
    Auto-check passed
  • UI/UX Design System Advisor

    Galaxy-Dawn/claude-scholar

    Turns a vague UI request into a concrete design system with style, palette, typography and layout guidance from a search script, plus stack-specific implementation advice.

    5.7k GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed
  • Daily Paper Digest

    Galaxy-Dawn/claude-scholar

    Finds recent arXiv and bioRxiv papers on a topic, narrows them in stages to one pick per field, and writes bilingual Chinese and English summaries.

    5.7k GitHub stars~1k tokensUpdated 17 days ago
    Auto-check passed
  • Nature Data

    Galaxy-Dawn/claude-scholar

    Prepare, audit, or revise Nature-ready Data Availability statements, data repository plans, dataset citations, and FAIR metadata checklists for manuscripts.

    5.7k GitHub starsUsed in 3 repos~1.6k tokens
    Auto-check passed

Categories

Questions about Planning With Files

What does Planning With Files do?

Keeps a long task on track by writing a plan, running notes and the final deliverable to markdown files on disk instead of relying on chat memory. This skill makes plain markdown files the agent's working memory for any task likely to take many tool calls, span phases, branch, pause or resume.md stores findings and research; and a separate deliverable file receives the final output.

When should I use Planning With Files?

Planning With Files fits situations like: starting a research task that will need many searches and a written result; working through a multi-phase change where progress must survive a pause or restart; keeping evidence and decisions in notes instead of long chat context.

How do I install Planning With Files in Claude Code?

Run `npx skills add Galaxy-Dawn/claude-scholar --skill planning-with-files -a claude-code`. Or copy the skill folder (skills/planning-with-files in Galaxy-Dawn/claude-scholar) into .claude/skills/planning-with-files in your project. Claude Code loads it when a task matches its description.

How do I install Planning With Files in Codex?

Run `npx skills add Galaxy-Dawn/claude-scholar --skill planning-with-files -a codex`. Or copy the skill folder (skills/planning-with-files in Galaxy-Dawn/claude-scholar) into .agents/skills/planning-with-files in your project. Codex loads it when a task matches its description.

Can I use Planning With Files in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Galaxy-Dawn/claude-scholar --skill planning-with-files -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/planning-with-files, .gemini/skills/planning-with-files, .github/skills/planning-with-files and .opencode/skills/planning-with-files in your project.

What does Planning With Files need to run?

SKILL.md names no scripts, command-line tools or credentials: Planning With Files is instructions for the agent only.

Does Planning With Files access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Planning With Files safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Planning With Files use?

Planning With Files is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Planning With Files use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Planning With Files?

Skills that share tags, products or a category with Planning With Files: MemPalace Recall for Planning (open-gsd/gsd-core, 10k stars), Planning with Files (OthmanAdi/planning-with-files, 27k stars), Planning With Files (OthmanAdi/planning-with-files, 27k stars) and Planning with Files for Kiro (OthmanAdi/planning-with-files, 27k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Planning With Files?

Galaxy-Dawn (a GitHub user) maintains it in Galaxy-Dawn/claude-scholar, which has 5,725 GitHub stars. The repository holds 34 skills in this directory. The repository was last updated on September 23, 2026.

Source: Galaxy-Dawn/claude-scholar on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.