Build
Code implementation mode. Use when you have an approved plan and are ready to build. Enforces code standards, security practices, and incremental implementation.
Install
$ agentstack add skill-anbturki-claude-toolkit-build ✓ 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 Used
- ✓ 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.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-anbturki-claude-toolkit-build) 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
Implement & Code
Approved plan only.
Before Writing Code
- Explain what you're about to do and why
- Break it down into steps the user can follow
- Show which files will be touched (if >3, explain the dependency chain)
- Wait for OK before proceeding
Code Standards
- Implement only what's immediately needed — solve the immediate problem, nothing more
- Follow existing patterns exactly — check how similar features are built and do the same
- Reuse existing code (DRY) — identify reusable utilities before writing anything new
- Each component/file should have ONE clear, focused purpose (Single Responsibility)
- Keep functions small and single-purpose
- Favor readability over cleverness — write code a junior can maintain
- Add comments for non-obvious logic; use meaningful variable and function names
- No
anytypes, no untypedobject, no TypeScript assertion bypasses - Minimize DOM nesting — keep structure flat, no redundant wrapper divs
- Keep component files under 200 lines when possible; separate logic from presentation
- Use composition over inheritance
- Use straightforward REST endpoints — no fancy patterns
- Use parameterized queries (never string concatenation for SQL)
- Validate all user input — assume it's hostile
- Never log or expose secrets, tokens, or credentials
- Never hardcode API keys, passwords, or secrets
After Writing Code
- Run the project's lint/format/typecheck command — fix any errors
- Run the project's test command — ensure no tests are broken
- If working from a task list, mark the task as completed
- Show: files created/modified, what was implemented (1-2 sentences)
Do NOT
- Write clever one-liners nobody can read
- Add dependencies for things we can write in 10 lines
- Over-engineer simple problems or create premature abstractions
- Refactor unrelated code while fixing a bug
- Change formatting or style in files you're not working on
- Disable CORS, SSL validation, or auth for convenience
- Commit .env files or credentials to git
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: anbturki
- Source: anbturki/claude-toolkit
- 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.