Skill

planning-with-files

Name: planning-with-files
Author: OthmanAdi

@OthmanAdi Updated 2026-10-17

Persistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and emits aggregate counts only; --replay may emit bounded nonce-framed excerpts. Optional gated mode can request continuation only when the host supports it and never runs commands declared in Markdown. The skill has no network upload path. Use for research or work needing 5+ tool calls.

agent-skillsautonomous-agentsclaudeclaude-codeclaude-code-skillsclaude-skillscodexcoding-agent

Install

git clone https://github.com/OthmanAdi/planning-with-files /tmp/planning-with-files && ln -s /tmp/planning-with-files/.agents/skills/planning-with-files ~/.claude/skills/planning-with-files

From README

Planning with Files Work like Manus: Use persistent markdown files as your "working memory on disk." FIRST: Restore Project State Before continuing, resolve the plan this task owns: Use the installed scripts/resolve-plan-dir.sh (or .ps1) with the task's PLANID and PWFPLANROOT. Read taskplan.md, progress.md, and findings.md from that one selected directory. A root taskplan.md must not override a selected .planning/ / plan. If an explicit selector is rejected, or multiple named plans exist without PLANID, stop plan recovery and correct the pin. Do not fall back to another task. Use the legacy project-root files only when no selector or named plan applies. Run git diff --stat to see code changes that may not yet be recorded in the planning files. All planning filenames below refer to this selected directory, even when the shell runs elsewhere. For parallel tasks, pin each host before starting it or use separate worktrees.