
Planning With Files (German)
Keeps persistent markdown plans on disk so the agent can track multi-step work across sessions
- Repository
- OthmanAdi/planning-with-files
- Stars
- 27,822
- Licence
- MIT
- Files
- 15 files
What it does
This skill teaches an AI agent to keep its working memory in plain markdown files (task_plan.md, findings.md, progress.md) inside the project instead of relying on chat history. Lifecycle hooks can inject the relevant plan back into the agent's context and check whether all phases are marked complete before it stops. It is written in German and is meant for research or tasks needing more than about five tool calls.
Great for
- Developers running long, multi-step coding or research tasks with an AI agent who want progress to survive context resets
- German-speaking users who want the planning instructions and templates in German
- Teams running parallel tasks who want separate plan folders per task
Skip it if
- Short one-off questions, where the planning overhead adds noise and no value
- Projects where the agent must not run shell scripts, since the hooks and helper scripts execute commands on the machine
- Environments without a shell or Python, since several scripts depend on sh, bash and python3
Try asking
- “Plan a multi-step refactor of this repository and keep progress in task_plan.md”
- “Research a library comparison and record findings in findings.md as you go”
- “Resume yesterday's migration task from the saved plan files”
- “Check whether all phases of the current plan are complete before finishing”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 15 original files, the MIT licence and an attribution note.
planning-with-files-de.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip planning-with-files-de.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip planning-with-files-de.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Only use --replay or --metadata on session history when you explicitly ask; both are opt-in and limited.
- Review the hook commands in SKILL.md before installing, since they run automatically on prompt, tool use and stop events.
- Set PWF_SCRIPT_DIR or install to a user-level path if the hook reports that the script was not found.
What's inside
- plan-inventory.md
- scripts/attest-plan.sh
- scripts/check-complete.sh
- scripts/gate-stop.sh
- scripts/init-session.sh
- scripts/ledger-append.sh
- scripts/ledger-summary.sh
- scripts/phase-status.sh
- scripts/plan-doctor.sh
- scripts/resolve-plan-dir.sh
- scripts/session-catchup.py
- scripts/set-active-plan.sh
- scripts/skill-hook.sh
- SKILL.md
- templates/findings.md
Redistributed unmodified from OthmanAdi/planning-with-files under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.