NoesisVision/nasde-toolkit
CLI for benchmarks & evals of AI coding agents — on tasks you already understand, using your Claude / Codex / Gemini individual subscriptions or API keys.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
GUARDRAILS
3/5
Blocks destructive commands · Pre-tool screening hook · No YOLO mode · details
Quality 20/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit NoesisVision/nasde-toolkit/.claude ./rig-nasde-toolkit # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit NoesisVision/nasde-toolkit/.claude/skills/nasde-benchmark-calibration .claude/skills/nasde-benchmark-calibration $ npx degit NoesisVision/nasde-toolkit/.claude/skills/nasde-benchmark-creator .claude/skills/nasde-benchmark-creator $ npx degit NoesisVision/nasde-toolkit/.claude/skills/nasde-benchmark-from-history .claude/skills/nasde-benchmark-from-history $ npx degit NoesisVision/nasde-toolkit/.claude/skills/nasde-benchmark-from-public-repos .claude/skills/nasde-benchmark-from-public-repos $ npx degit NoesisVision/nasde-toolkit/.claude/skills/nasde-benchmark-runner .claude/skills/nasde-benchmark-runner $ npx degit NoesisVision/nasde-toolkit/.claude/skills/nasde-dev .claude/skills/nasde-dev $ npx degit NoesisVision/nasde-toolkit/examples/ddd-architectural-challenges/variants/claude-ntcoding-tactical-ddd-anemic-tuned/skills/tactical-ddd .claude/skills/tactical-ddd $ npx degit NoesisVision/nasde-toolkit/examples/nasde-dev-skill/variants/claude-nasde-dev-full-stack/skills/python-best-practices .claude/skills/python-best-practices $ npx degit NoesisVision/nasde-toolkit/examples/nasde-dev-skill/variants/claude-nasde-dev-full-stack/skills/python-testing .claude/skills/python-testing $ npx degit NoesisVision/nasde-toolkit/examples/refactoring-skill/variants/claude-refactoring-skill/skills/refactor .claude/skills/refactor
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "jq -r '.tool_input.command' | grep -q 'git commit' && uv run ruff check src/ tests/ && uv run ruff format --check src/ tests/ && uv run mypy src/nasde_toolkit/ && uv run pytest -q || true"
}
]
}
]
}
} Skills (10)
nasde-benchmark-calibrationnasde-benchmark-creatornasde-benchmark-from-historynasde-benchmark-from-public-reposnasde-benchmark-runnernasde-devtactical-dddpython-best-practicespython-testingrefactor
Hooks (1)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Bash | jq -r '.tool_input.command' | grep -q 'git commit' && uv run ruff check src/ tests/ && uv run ruff format --check src/ tests/ && uv run mypy src/nasde_toolkit/ && uv run pytest -q || true |
Similar rigs
sjhalani7/vaen
Package your AI coding harness into a portable .agent file, and share it across repos, teams, & the community without ever having to copy-paste instructions, skills, MCP config, or secrets.
Minimalist 20 tok · · Q0
regression-io/coder-config
Configuration manager for AI coding tools - Claude Code, Gemini CLI, Codex CLI, Antigravity. Manage MCPs, rules, permissions, memory, and workstreams.
Minimalist 251 tok · · Q0
jefflester/claude-skills-supercharged
A "supercharged" implementation of Claude Code Skills – using Haiku prompt analysis/critical skill scoring and skill auto-injection for friction-free, context-driven workflows.
Pragmatist 256 tok · · Q15
mirosval/dotfiles
macOS, nix, neovim
Pragmatist 57 tok · · Q0