File-based planning for complex tasks. Use persistent markdown files as working memory to survive context resets. Creates task_plan.md, findings.md, and progress.md. Use for any task requiring >5 tool calls, research projects, or multi-step implementations.
Security Analysis
high confidenceThe skill's inputs, files, and scripts are consistent with its stated purpose of using on-disk markdown as persistent planning memory and do not request unrelated credentials or install remote code.
Name/description match the behavior: the skill creates and manages three markdown files and provides helper scripts and templates to treat the filesystem as persistent memory. There are no unrelated environment variables, binaries, or config paths requested.
SKILL.md instructs the agent to create/read/write task_plan.md, findings.md, and progress.md, and to run simple local commands (ls, cat, git diff --stat). This is coherent with the planning purpose. Note: the skill intentionally instructs persistent file creation in the project root and to log errors and discoveries; users should be aware that anything written to these files will persist on disk (and in git history if committed).
Instruction-only skill with no install spec that downloads/executes remote archives. Helper scripts are included in the package; there is no installer that fetches arbitrary code from untrusted URLs.
Skill requires no environment variables, credentials, or config paths. The files and scripts operate on local files only, which is proportionate to the stated functionality.
always:false and no elevated privileges requested. The skill writes files in the project directory and includes small helper scripts; this is consistent with its purpose and does not modify other skills or system-wide settings.
Guidance
This skill is internally coherent and appears to do what it says — create and maintain three markdown files as persistent planning memory. Before installing or running it, consider: 1) The planning files (task_plan.md, findings.md, progress.md) will be created in your project root and persist on disk (and in your git history if committed). Do not log secrets or sensitive data there. 2) Review the included scripts (init-session.sh, check-complete.sh) — they are simple shell scripts that create/check files, but you should inspect them and run in a safe folder first. 3) If you use version control, consider adding these files to .gitignore or keeping them in a sandbox workspace to avoid accidental leakage. 4) The package source/homepage is unknown; although there are no network endpoints or remote installs in the package itself, prefer installing from a trusted source or inspecting the files locally before adding to long-running agents. 5) The agent can invoke skills autonomously by default; if you plan to run this skill in an autonomous agent, be mindful that it will create/modify files without prompting. If you want further checks (e.g., to ensure it never writes outside a specific directory), provide that constraint and I can point out the exact lines to change.
Latest Release
v1.0.0
- Initial release of planning-with-files skill. - Enables robust file-based planning for complex, multi-step tasks. - Introduces use of three persistent markdown files—task_plan.md, findings.md, progress.md—as working memory to overcome context resets. - Provides clear usage guidelines, workflow, error-handling protocol, and anti-patterns. - Includes templates and helper scripts for easy setup and best practices.
More by @wpank
Published by @wpank on ClawHub
