AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Planning with Files

Keeps task_plan.md, findings.md and progress.md on disk so multi-step work survives /clear, compaction and context loss.

AutomationIntermediate★ 26,060⑂ 2,177AI score 10/10Last updated: Aug 9, 2026

What it does

Brings Manus-style "working memory on disk" to Claude Code. Before any complex task, it creates and maintains three files in your project directory:

  • task_plan.md — phases, status, next step, decisions journal
  • findings.md — everything discovered during research
  • progress.md — session log, test results, errors

UserPromptSubmit / PreToolUse / PreCompact / Stop hooks re-inject the plan into context automatically, and session-catchup.py recovers state after /clear or compaction. It also ships battle-tested rules (save findings every 2 view/search operations, 3-strike error protocol, 5-question reboot test), parallel plans under .planning/<date-slug>/, SHA-256 plan attestation, opt-in autonomous/gated modes with a completion gate, and a parallel-write guard that warns when another session clobbers progress.

Who it's for

  • Anyone running refactors, migrations or research that span many steps and tool calls
  • People tired of losing the thread when context fills up or after /clear
  • Developers juggling several tasks in one repo who want isolated plans
  • Users running long autonomous agent loops that need a termination oracle and runaway guards

Examples

  1. "Migrate the legacy auth module to OAuth" → a 6-phase plan lands in task_plan.md; even after /clear, the next turn re-reads the plan and resumes exactly where it stopped.
  2. Two workstreams in one repo: ./scripts/init-session.sh "Backend Refactor" and "Incident Investigation", then switch with set-active-plan.sh or pin a terminal via PLAN_ID.
  3. Overnight build pipeline: init-session.sh --gated "Build Pipeline" turns on the Stop gate so the agent won't quit with an in_progress phase, while the block cap and stall detector prevent infinite loops.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/OthmanAdi/planning-with-files/HEAD/skills/planning-with-files/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the skills/planning-with-files folder from the GitHub repo OthmanAdi/planning-with-files into my ~/.claude/skills/othmanadi-planning-with-files-11/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/OthmanAdi/planning-with-files.git /tmp/planning-with-files && mkdir -p ~/.claude/skills && cp -r /tmp/planning-with-files/skills/planning-with-files ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repo to a temp folder: git clone https://github.com/OthmanAdi/planning-with-files.git /tmp/planning-with-files
  2. Create the skills folder if needed: mkdir -p ~/.claude/skills
  3. Copy the skill in: cp -r /tmp/planning-with-files/skills/planning-with-files ~/.claude/skills/
  4. (Recommended) To also get the /plan-goal and /plan-loop slash commands, install via the plugin route instead: run /plugin marketplace add OthmanAdi/planning-with-files in Claude Code, then /plugin install.
  5. Restart Claude Code so the hooks register.
  6. Open a project and ask "plan this out step by step" — task_plan.md will be created in the project root.
  7. If the hooks seem quiet, run sh ~/.claude/skills/planning-with-files/scripts/plan-doctor.sh for a self-check. Note that session-catchup.py requires python3.
View source on GitHub ↗License: MIT