mitchmolstad/claude-spark
Project template for Claude Code. Keep building useful stuff as things get complex through smart scaffolding and memory-that-matters. Persistent memory across sessions via structured documentation and skills.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit mitchmolstad/claude-spark/.claude ./rig-claude-spark # 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 mitchmolstad/claude-spark/.claude/skills/adr .claude/skills/adr $ npx degit mitchmolstad/claude-spark/.claude/skills/deploy-and-verify .claude/skills/deploy-and-verify $ npx degit mitchmolstad/claude-spark/.claude/skills/done .claude/skills/done $ npx degit mitchmolstad/claude-spark/.claude/skills/frontend-design .claude/skills/frontend-design $ npx degit mitchmolstad/claude-spark/.claude/skills/parallel-work .claude/skills/parallel-work $ npx degit mitchmolstad/claude-spark/.claude/skills/spark .claude/skills/spark $ npx degit mitchmolstad/claude-spark/.claude/skills/start .claude/skills/start $ npx degit mitchmolstad/claude-spark/.claude/skills/strategy .claude/skills/strategy $ npx degit mitchmolstad/claude-spark/.claude/skills/systematic-debugging .claude/skills/systematic-debugging $ npx degit mitchmolstad/claude-spark/.claude/skills/test-driven-development .claude/skills/test-driven-development $ npx degit mitchmolstad/claude-spark/.claude/skills/verification-before-completion .claude/skills/verification-before-completion $ npx degit mitchmolstad/claude-spark/.claude/skills/vertical-slice .claude/skills/vertical-slice
$ curl -fsSL --create-dirs -o .claude/agents/doc-updater.md https://raw.githubusercontent.com/mitchmolstad/claude-spark/master/.claude/agents/doc-updater.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/mitchmolstad/claude-spark/master/.claude/agents/security-reviewer.md
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": "bash .claude/scripts/guard-bash.sh"
}
]
},
{
"matcher": "Edit|Write",
"hooks": [
{
"type": "command",
"command": "bash .claude/scripts/guard-env.sh"
}
]
}
]
}
} Skills (12)
adrdeploy-and-verifydonefrontend-designparallel-worksparkstartstrategysystematic-debuggingtest-driven-developmentverification-before-completionvertical-slice
Subagents (2)
| doc-updater | — |
| security-reviewer | — |
Hooks (6)
| event | matcher | runs |
|---|---|---|
| SessionStart | startup|compact | bash .claude/scripts/rehydrate.sh |
| Stop | * | bash .claude/scripts/doc-sync.sh |
| PreToolUse | Bash | bash .claude/scripts/guard-bash.sh |
| PreToolUse | Edit|Write | bash .claude/scripts/guard-env.sh |
| TeammateIdle | * | bash .claude/scripts/teammate-gate.sh |
| TaskCompleted | * | bash .claude/scripts/task-verify.sh |
Similar rigs
taiyyoson/my-claude-code
Version-controlled Claude Code setup with three working modes
Pragmatist 1.1k tok ·
nicolasaudran/claude-dotfiles
—
Pragmatist 320 tok ·
raiki61/claude-plugins
Two Claude Code loops that keep reviewing and researching until they reach a fixed point: the implementer and the grader are held in separate contexts, and the machine may only ever declare failure, never convergence. Japanese only for now.
Orchestrator 1.2k tok ·
RichardBray/dotfiles
My personal configuration files and settings
Skill Collector 671 tok ·