
Planning with Files (Arabic)
Keeps persistent Markdown plan files on disk so an agent can track multi-step work across long tasks.
- Repository
- OthmanAdi/planning-with-files
- Stars
- 27,822
- Licence
- MIT
- Files
- 15 files
What it does
This skill makes an AI agent keep its working memory in plain Markdown files inside your project: a task plan, a findings file, and a progress log. Lifecycle hooks re-inject the plan's context at key moments, such as before each tool call and when a prompt is submitted, and a completion check reports whether all phases are finished. It is written in Arabic and is meant for research or work that needs five or more tool calls.
Great for
- Developers running long, multi-step agent tasks who want resumable progress tracking
- Users who prefer Arabic-language planning templates and status messages
- Teams that want plans stored as versioned files in the project folder
Skip it if
- Short one-off questions, since the overhead of plan files is not worth it (the skill itself targets tasks with 5+ tool calls)
- Environments where hooks running shell scripts on every tool call are not acceptable, because the hooks execute scripts repeatedly during a session
- Sensitive projects where you have not reviewed the scripts, since they run locally and can read and write project files
Try asking
- “Start a multi-step research task and keep the plan in task_plan.md so I can resume it later”
- “Initialize a new planning session for a refactoring project named Billing API”
- “Check whether all phases in my current plan are marked complete”
- “Lock the finished plan with an attestation so later edits are flagged as tampered”
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-ar.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip planning-with-files-ar.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip planning-with-files-ar.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
- Run init-session.sh once per task and pin the agent to the printed PLAN_ID so parallel sessions do not mix plans
- Review the hook commands in SKILL.md before installing, since they run automatically on prompt, tool, and stop events
- Use the metadata mode of session-catchup.py rather than replay; replay outputs session excerpts that should be treated as untrusted data
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.