Install
$ agentstack add skill-cassmtnr-claude-code-starter-claude-code-starter ✓ 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
Claude Code Starter
You are setting up Claude Code configuration for a project. Follow the flow below to analyze the project and generate all .claude/ configuration files.
Step 1: Detect Project Type
Check if this is a new project (empty or " ---
Instructions to update `.claude/state/task.md` with new task, set status to "In Progress".
### `.claude/commands/status.md`
```yaml
---
allowed-tools: ["Read", "Glob", "Bash(git status)"]
description: "Show current task and session state"
---
Instructions to read task.md, show git status, summarize current state.
.claude/commands/done.md
---
allowed-tools: ["Read", "Write", "Edit", "Glob", "Bash(git:*)", "Bash(bun test)"]
description: "Mark current task complete"
---
Instructions to run tests, lint, verify, update task.md status to "Done".
.claude/commands/analyze.md
---
allowed-tools: ["Read", "Glob", "Grep"]
description: "Deep analysis of a specific area"
argument-hint: ""
---
Instructions to perform thorough analysis of specified area.
.claude/commands/code-review.md
---
allowed-tools: ["Read", "Glob", "Grep", "Bash(git diff)"]
description: "Review code changes for quality and security"
---
Instructions to review staged/unstaged changes.
Output Summary
After generating all files, output a brief summary:
- List of files created
- Any gaps found (missing config files, unclear patterns)
- Suggested next steps
Important Guidelines
- Be specific, not generic. Every file must contain project-specific content.
- Reference real files. Use
path/to/file.ts:lineNumberformat. - Use actual commands. Reference the project's real test/lint/build commands.
- Skip what doesn't apply. Don't generate framework skills for frameworks not in use.
- Respect existing files. If
.claude/files exist, read and preserve manually-added content.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: cassmtnr
- Source: cassmtnr/claude-code-starter
- License: MIT
- Homepage: https://cassmtnr.github.io/claude-code-starter/
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.