SmartAndPoint/ProjectStore
Decisions, specs and stories as plain markdown, for every coding agent. Code changes. Context stays.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit SmartAndPoint/ProjectStore/agents ./rig-projectstore/agents $ npx degit SmartAndPoint/ProjectStore/commands ./rig-projectstore/commands $ npx degit SmartAndPoint/ProjectStore/skills ./rig-projectstore/skills $ npx degit SmartAndPoint/ProjectStore/hooks ./rig-projectstore/hooks
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 <redacted>-adr .claude/skills/projectstore-adr $ npx degit <redacted>-agents .claude/skills/projectstore-agents $ npx degit <redacted>-archaeologist .claude/skills/projectstore-archaeologist $ npx degit <redacted>-bind .claude/skills/projectstore-bind $ npx degit <redacted>-clerk .claude/skills/projectstore-clerk $ npx degit <redacted>-codemap .claude/skills/projectstore-codemap $ npx degit <redacted>-concept .claude/skills/projectstore-concept $ npx degit <redacted>-critic .claude/skills/projectstore-critic $ npx degit <redacted>-decision-detector .claude/skills/projectstore-decision-detector $ npx degit <redacted>-doctor .claude/skills/projectstore-doctor $ npx degit <redacted>-epic .claude/skills/projectstore-epic $ npx degit <redacted>-graph .claude/skills/projectstore-graph $ npx degit <redacted>-kanban .claude/skills/projectstore-kanban $ npx degit <redacted>-librarian .claude/skills/projectstore-librarian $ npx degit <redacted>-meeting .claude/skills/projectstore-meeting $ npx degit <redacted>-peer-reviewer .claude/skills/projectstore-peer-reviewer $ npx degit <redacted>-planner .claude/skills/projectstore-planner $ npx degit <redacted>-reconcile .claude/skills/projectstore-reconcile $ npx degit <redacted>-research .claude/skills/projectstore-research $ npx degit <redacted>-review .claude/skills/projectstore-review $ npx degit <redacted>-reviewer .claude/skills/projectstore-reviewer $ npx degit <redacted>-runbook .claude/skills/projectstore-runbook $ npx degit <redacted>-scaffold .claude/skills/projectstore-scaffold $ npx degit <redacted>-search .claude/skills/projectstore-search $ npx degit <redacted>-spec .claude/skills/projectstore-spec $ npx degit <redacted>-status .claude/skills/projectstore-status $ npx degit <redacted>-statusline .claude/skills/projectstore-statusline $ npx degit <redacted>-story-completion .claude/skills/projectstore-story-completion $ npx degit <redacted>-story .claude/skills/projectstore-story $ npx degit <redacted>-vault-communication .claude/skills/projectstore-vault-communication
$ curl -fsSL --create-dirs -o .claude/agents/archaeologist.md https://raw.githubusercontent.<redacted>.md $ curl -fsSL --create-dirs -o .claude/agents/clerk.md https://raw.githubusercontent.<redacted>.md $ curl -fsSL --create-dirs -o .claude/agents/critic.md https://raw.githubusercontent.<redacted>.md $ curl -fsSL --create-dirs -o .claude/agents/librarian.md https://raw.githubusercontent.<redacted>.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.<redacted>.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.<redacted>.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| projectstore | local / custom | 2.5k |
Skills (30)
projectstore-adrprojectstore-agentsprojectstore-archaeologistprojectstore-bindprojectstore-clerkprojectstore-codemapprojectstore-conceptprojectstore-criticprojectstore-decision-detectorprojectstore-doctorprojectstore-epicprojectstore-graphprojectstore-kanbanprojectstore-librarianprojectstore-meetingprojectstore-peer-reviewerprojectstore-plannerprojectstore-reconcileprojectstore-researchprojectstore-reviewprojectstore-reviewerprojectstore-runbookprojectstore-scaffoldprojectstore-searchprojectstore-specprojectstore-statusprojectstore-statuslineprojectstore-story-completionprojectstore-storyprojectstore-vault-communication
Subagents (6)
| archaeologist model: opus | Opus (max-effort) decision archaeologist for brownfield onboarding. Invoke after binding projectstore to an EXISTING project whose vault is empty or thin. Scans the codebase + git history for decision |
| clerk model: sonnet | Sonnet (max-effort) write ceremony executor for projectstore vaults — the roster's sole write-capable agent, and its least autonomous. NEVER auto-delegate to it; it is invoked only by projectstore com |
| critic model: opus | Opus (max-effort) adversarial critic for projectstore artifacts (ADR / research / epic / story) and design proposals. Pre-commits to likely problems, verifies claims against source, rates assumptions, |
| librarian model: opus | Opus (max-effort) semantic vault curator for projectstore vaults. Invoke periodically, before releases, or after heavy vault growth — AFTER running /projectstore:doctor (doctor catches mechanical drif |
| planner model: opus | Opus (max-effort) EPIC-IMPLEMENTATION planner for projectstore-bound projects — a narrow, vault-aware role, NOT a general software planner. Invoke BEFORE implementing an epic/story. Reads the vault (e |
| reviewer model: opus | Opus (max-effort) STORY-CONFORMANCE reviewer for projectstore-bound projects — a narrow, vault-aware role, NOT a general code reviewer. Invoke AFTER writing code, BEFORE committing or marking a story |
Slash commands (19)
/adr/bind/codemap/concept/doctor/epic/graph/kanban/meeting/reconcile/research/review/runbook/scaffold/search/spec/status/statusline/story
Similar rigs
BillDX/spicy-to-dark-factory-starter
Workshop starter for 'From Spicy Autocomplete to Dark Factory: Agentic Coding in Practice' — a FastAPI mini-app with a full Claude Code harness (agents, slash commands, hooks, sandbox settings) and self-paced exercises.
Orchestrator 706 tok ·
fjerbi/claude-code-arsenal
A tested Claude Code operating system for efficient, reliable, and focused software engineering. Includes global instructions, workflows, rules, and tools designed to minimize wasted tokens, prevent hallucinations and unnecessary loops, enf
YOLO Cowboy 4.0k tok ·
Alex5350/arsenal
Provider-agnostic AI development hub: one docs/ source of truth for skills, standards, tiered model routing, and work tracking across Claude Code, Codex CLI, OpenCode, and GitHub Copilot
Pragmatist 1.7k tok ·
orynvn/claude-workspace-setup
A project template for Claude Code CLI — opinionated, token-efficient, and built for multi-agent workflows.
Orchestrator 22.3k tok ·