planning-with-files

planning-with-files is a skill for Claude Code from Galaxy-Dawn/claude-scholar. It costs 61 tokens per session (1,020 once invoked), scanned A, original, MIT.

A file-based planning method for complex work that keeps the plan, findings, progress, and final deliverable in separate Markdown files.

In plain words
What is it for?
Use it to plan multi-step coding or research tasks, track progress, preserve findings, and resume work later.
Why use it?
It prevents important decisions and research notes from being lost in a long conversation, especially when work spans several steps or sessions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the TodoWrite tool; mentions Codex.

Part of the claude-scholar plugin — 45 skills, 34 commands, 6 agents, 5 hooks shipped together

Good fit Use it to plan multi-step coding or research tasks, track progress, preserve findings, and resume work later.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/galaxy-dawn/claude-scholar/planning-with-files
About the project

Claude Scholar is a semi-automated research assistant for academic research and software development, supporting literature review, coding, experiments, reporting, writing, and project knowledge management. Computer science and AI researchers use it across the research workflow with several coding-agent platforms; the catalogue contains its skills, commands, agents, hooks, plugin, and instruction.

Galaxy-Dawn/claude-scholar · 5,419 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Galaxy-Dawn/claude-scholar --skill planning-with-files
Clone the repo
git clone --depth 1 https://github.com/Galaxy-Dawn/claude-scholar

Made for: Claude Code.

Or install claude-scholar, the plugin that ships this one along with the rest of its 45 skills, 34 commands, 6 agents, 5 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for planning-with-files

README.md
[![agentmods](https://agentmods.dev/badge/skills/galaxy-dawn/claude-scholar/planning-with-files/github.svg)](https://agentmods.dev/skills/galaxy-dawn/claude-scholar/planning-with-files)
Your own site
<a href="https://agentmods.dev/skills/galaxy-dawn/claude-scholar/planning-with-files"><img src="https://agentmods.dev/badge/skills/galaxy-dawn/claude-scholar/planning-with-files/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for planning-with-files

Your own site · 80×15
<a href="https://agentmods.dev/skills/galaxy-dawn/claude-scholar/planning-with-files"><img src="https://agentmods.dev/badge/skills/galaxy-dawn/claude-scholar/planning-with-files.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,020 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Memory Poisoning · line 63
    Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
    Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.01020
Opus 5 $0.00030 $0.00510
Sonnet 5 $0.00012 $0.00204
Haiku 4.5 $0.00006 $0.00102

Measured 8d ago against content hash 6b527bee3d60, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

planning-with-files scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/planning-with-files/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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:

Read task_plan.md  # Refresh goals in attention window

After each phase:

Edit task_plan.md  # Mark [x], update status

When storing information:

Write notes.md     # Don't stuff context, store in file

task_plan.md Template

Create this file FIRST for any complex task:

# 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]

Read the full file on GitHub · 172 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 172 lines · 61 tokens per session scan A 6b527bee3d60

Subscribe to this mod's changes

planning-with-files is a skill published in the GitHub repository Galaxy-Dawn/claude-scholar (5,419 stars, last pushed 15d ago), licensed MIT. It adds 61 tokens to every session and 1,020 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

boss-briefing

Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.

sehoon787/my-codex · 23 tokens

tfx-wt

A natural-language controller for tabs and panes in Windows Terminal, Microsoft's command-line application for Windows.

tellang/triflux · 125 tokens

codex-hud

Show Codex workspace context with local config, git state, hooks, and project hints. Standalone mode can show an expanded snapshot; patched Codex TUI footer mode is single-line. Use when the user says "codex-hud", "show Codex HUD", "status HUD", "workspace snapshot", or asks for richer Codex context.

brandonwie/codex-hud · 76 tokens

handoff

Write a state capsule so the next session — or a different agent/harness — can resume unfinished work without re-deriving context. Use when a session is ending with work incomplete, when the user says "handoff", "pack up", "ส่งต่อ", "continue tomorrow", when switching between Claude Code and Codex mid-task, or when…

ohm41321/luciazero · 86 tokens

tfx-remote

A single command group for managing local and remote coding-agent sessions. It includes commands for configuring hosts, creating sessions, listing them, reconnecting, sending messages, resuming, ending, and checking connections.

tellang/triflux · 71 tokens

unlazy

Evidence-backed completion discipline for substantial tasks. Use when the user explicitly asks for exhaustive follow-through, every requested item finished, a long autonomous task to continue until measurable completion, or invokes unlazy, depth-tree, or gate-based execution. Do not use for trivial edits, factual…

cmdr-chara/codex-toolkit · 75 tokens