keith-nielsen/2026-AI-Value-Memory-Mining
Value Memory Mining personal knowledge system — OpenSpec SDD showcase + forkable vault template
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
GUARDRAILS
4/5
Blocks destructive commands · Pre-tool screening hook · No YOLO mode · Sandbox or ask-first rules · details
Quality 38/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit keith-nielsen/2026-AI-Value-Memory-Mining/.claude ./rig-2026-ai-value-memory-mining # 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 keith-nielsen/2026-AI-Value-Memory-Mining/.claude/skills/openspec-apply-change .claude/skills/openspec-apply-change $ npx degit keith-nielsen/2026-AI-Value-Memory-Mining/.claude/skills/openspec-archive-change .claude/skills/openspec-archive-change $ npx degit keith-nielsen/2026-AI-Value-Memory-Mining/.claude/skills/openspec-explore .claude/skills/openspec-explore $ npx degit keith-nielsen/2026-AI-Value-Memory-Mining/.claude/skills/openspec-propose .claude/skills/openspec-propose $ npx degit keith-nielsen/2026-AI-Value-Memory-Mining/.claude/skills/openspec-sync-specs .claude/skills/openspec-sync-specs
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Bash(gh pr:*)",
"Bash(gh issue:*)",
"Bash(gh project:*)",
"Bash(gh repo view:*)",
"Bash(gh api graphql:*)",
"Edit(/40-Treasury/**)",
"Edit(/99-Operations/**)",
"Edit(/.claude/**)",
"Edit(/96-Runbooks/**)",
"Edit(/97-Molds/**)",
"Bash(gh pr:*)",
"Bash(gh issue:*)",
"Bash(gh project:*)",
"Bash(gh repo view:*)",
"Bash(gh api graphql:*)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "python3 \"$CLAUDE_PROJECT_DIR/.claude/hooks/outbound-publish-guard.py\""
},
{
"type": "command",
"command": "python3 \"$CLAUDE_PROJECT_DIR/.claude/hooks/gh-invocation-guard.py\""
},
{
"type": "command",
"command": "python3 \"$CLAUDE_PROJECT_DIR/.claude/hooks/outbound-publish-guard.py\""
},
{
"type": "command",
"command": "python3 \"$CLAUDE_PROJECT_DIR/.claude/hooks/gh-invocation-guard.py\""
}
]
}
]
},
"sandbox": {
"enabled": true
}
} Skills (5)
Hooks (8)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Bash | python3 "$CLAUDE_PROJECT_DIR/.claude/hooks/outbound-publish-guard.py" |
| PreToolUse | Bash | python3 "$CLAUDE_PROJECT_DIR/.claude/hooks/gh-invocation-guard.py" |
| SessionStart | * | echo "STANDING CONDUCT RULES — read $CLAUDE_PROJECT_DIR/vault-template/96-Runbooks/agent-conduct-standing-rules.md in full before acting; they outrank ordinary task instructions."; cat "$CLAUDE_PROJECT_DIR/vault-template/96-Runbooks/session |
| Stop | * | python3 "$CLAUDE_PROJECT_DIR/.claude/hooks/relay-conformance-guard.py" |
| PreToolUse | Bash | python3 "$CLAUDE_PROJECT_DIR/.claude/hooks/outbound-publish-guard.py" |
| PreToolUse | Bash | python3 "$CLAUDE_PROJECT_DIR/.claude/hooks/gh-invocation-guard.py" |
| SessionStart | * | echo "STANDING CONDUCT RULES — read $CLAUDE_PROJECT_DIR/96-Runbooks/agent-conduct-standing-rules.md in full before acting; they outrank ordinary task instructions."; cat "$CLAUDE_PROJECT_DIR/96-Runbooks/session-bootstrap-loader.md" 2>/dev/n |
| Stop | * | python3 "$CLAUDE_PROJECT_DIR/.claude/hooks/relay-conformance-guard.py" |
Slash commands (7)
/opsx/apply/opsx/archive/opsx/explore/opsx/propose/opsx/sync/vmm-session-rebooted/vmm-session-rebooted
Permissions
deny (15)
Bash(gh pr:*)
Bash(gh issue:*)
Bash(gh project:*)
Bash(gh repo view:*)
Bash(gh api graphql:*)
Edit(/40-Treasury/**)
Edit(/99-Operations/**)
Edit(/.claude/**)
Edit(/96-Runbooks/**)
Edit(/97-Molds/**)
Bash(gh pr:*)
Bash(gh issue:*)
Bash(gh project:*)
Bash(gh repo view:*)
Bash(gh api graphql:*)
ask (0)
—
allow (1)
WebFetch(domain:github.com)
Similar rigs
sathish316/pied-piper
Pied Piper is a team of AI SubAgents that can autonomously/semi-autonomously work on long-running or complex coding tasks with full End-to-end tracking and human-in-the-loop approvals. Subagents can run on Claude Code, Coding CLIs that supp
Pragmatist 271 tok · · Q0
sirshecomesthisway/squid-pet
Open-source living companion for AI-native coders — brings your agents to life, giving you a new interface to see, understand, and interact with AI agents.
Pragmatist 1.9k tok · · Q0
DavidDingXu/learn-ai-coding
面向程序员的 AI Coding 系统课程|42 篇完整文章 + 2 个可运行项目,覆盖 Codex / Claude Code、上下文工程、SDD / OpenSpec、测试调试、Skill / MCP 与真实需求交付。
Pragmatist 271 tok · · Q0
ForceInjection/OpenSpec-practise
OpenSpec Practical Guide
Pragmatist 2.0k tok · · Q0