Planning with Files
Persistent file-based planning for multi-step agent work — task plans, findings, progress on disk
- What
- Persistent file-based planning for multi-step agent work — task plans, findings, progress on disk
- Cost
- Free
- Needs
- an agent that supports lifecycle hooks and shell commands; shell access for the hook scripts
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — persistent file-based planning for long agent work: keep `task_plan.md`, `findings.md` and `progress.md` on disk, with lifecycle hooks that inject project planning context at prompt submit, pre/post tool use, stop and pre-compact — plus automatic recovery that reads project planning files only. The skill declares no network upload path; the gated mode requests continuation only when the host supports it and never runs commands declared in Markdown. By @othmanadi, listed here with credit to its creator. Honest caveats: it installs shell hooks into your agent's lifecycle — understand what they run before enabling; the file-based approach shines at 5+ tool calls and is overhead for trivial tasks. Skill Harbor never reviews the code, review it yourself before use.
Version:
Quick answer
Planning with Files is a free Muse skill for persistent file-based planning of multi-step agent work. It keeps task_plan.md, findings.md and progress.md on disk, with lifecycle hooks that inject project planning context at prompt submit, before and after tool use, at stop and before compaction, plus automatic recovery that reads project planning files only.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit 41f60aeStep 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: an agent that supports lifecycle hooks and shell commands; shell access for the hook scripts Install "Planning with Files" for me. Persistent file-based planning for multi-step agent work — task plans, findings, progress on disk Repository: https://raw.githubusercontent.com/othmanadi/planning-with-files/41f60aeca8bae0b145ec0e9421a7abd747ae2b69/.agents/skills/planning-with-files/SKILL.md Pinned version: install the code at commit 41f60aeca8bae0b145ec0e9421a7abd747ae2b69 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file for the othmanadi-planning-with-files skill from the repository into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "othmanadi-planning-with-files". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. any accounts, API keys, or CLI tools mentioned in the prerequisites above). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. Never ask me to paste secrets in chat — credentials go through the secure vault or environment variables. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 41f60ae · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 18, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.