Install
$ agentstack add skill-danielstormapps-claude-code-skills-write-plan ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Write a comprehensive implementation plan based on the requirements described below. Use ultrathink mode. Follow these instructions precisely:
- Research first. Explore the codebase thoroughly before writing anything. Read every relevant file. Trace call chains, delegate patterns, and data flow end-to-end. Reference exact file paths and line numbers. Assume nothing — verify everything by reading the code.
- Create the plan file. Add a new markdown file to the
plans/directory. Choose a clear, descriptive kebab-case filename (e.g.,feature-name-implementation.md). Use your best judgment for the name.
- Structure the plan with these sections:
- Overview — What this plan accomplishes and why. Include
**Status:** Not Started. - Current State — How the relevant code works today, with file paths, line numbers, and code snippets. Trace the full flow.
- Target Behavior — What should change and how it should work when complete.
- File Changes — Table of files to modify and/or create, with a summary of changes per file.
- Implementation — Organized into logical phases. Each phase should have a clear title, the files it touches, and detailed before/after code showing exact changes. Phases should be ordered so each builds on the previous.
- Implementation Checklist — Mirror the phases with
- [ ]checkbox items for tracking progress. - Dependencies — Table of existing components being reused (component, location, role).
- Out of Scope — Explicit list of what this plan intentionally does not cover.
- Additional sections (Edge Cases, Design Decisions, Notes) as warranted.
- Quality standards:
- Every file path, method name, property name, and line number must come from actually reading the code — never guess.
- Code snippets must match the project's Swift style (explicit types,
elseon its own line,guardfor early exits, no+=, etc.). - Phases should be small enough to implement and commit independently.
- The plan should be detailed enough that someone could implement it without asking questions.
- Do not stop to ask questions. Make reasonable decisions and document your rationale in the plan.
- When finished, commit the plan file and push. Reply here with the plan filename and a brief summary of what it covers.
$ARGUMENTS
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: DanielStormApps
- Source: DanielStormApps/claude-code-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.