Install
$ agentstack add skill-carbeneai-forge-governance ✓ 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 No
- ✓ 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.
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
Governance
Organizational intelligence for PAI, cherry-picked from Paperclip's zero-human-company model and adapted for CLI-first personal AI infrastructure.
Workflow Routing
| Action | Trigger | Tool/Config | |--------|---------|-------------| | Budget Review | "budget report", "agent spending", "cost tracking" | tools/BudgetReport.ts | | Org Chart | "org chart", "show team", "agent hierarchy" | tools/OrgChart.ts | | Goal Management | "goals", "goal context", "why are we doing this" | tools/GoalManager.ts | | Approval Check | "approval needed", "can I deploy", "governance gate" | tools/ApprovalGate.ts | | Standing Orders | "standing orders", "heartbeat", "scheduled agents" | tools/StandingOrders.ts | | Config Export | "export config", "backup PAI", "portable config" | tools/ConfigExport.ts | | Config Import | "import config", "restore PAI", "load config" | tools/ConfigImport.ts | | Task Locking | "lock task", "task checkout", "atomic task" | tools/TaskLock.ts |
Features
1. Budget Controls
Track and limit per-agent spending with cost estimates based on model pricing.
# Show spending report for current month
bun tools/BudgetReport.ts
# Compare against budget limits
bun tools/BudgetReport.ts --budget
# Filter by agent
bun tools/BudgetReport.ts --agent hiram --period week
Config: config/budgets.yml — per-agent monthly limits with alert thresholds.
2. Approval Gates
Human-in-the-loop governance for high-impact actions via Telegram.
# Check if action needs approval
bun tools/ApprovalGate.ts check deploy --agent hiram
# Request approval (sends Telegram, waits for response)
bun tools/ApprovalGate.ts request deploy --agent hiram --action "Push to carbene.ai production"
# List all gates
bun tools/ApprovalGate.ts list
Config: config/approvals.yml — gate definitions with Telegram integration.
3. Goal Ancestry
Every task traces back to a company goal. Provides "why" context for agent prompts.
# Show goal hierarchy
bun tools/GoalManager.ts list
# Trace project to goal
bun tools/GoalManager.ts trace P4
# Get injectable context block for agent prompts
bun tools/GoalManager.ts context P1
Config: goals/goals.yml — goal hierarchy with projects.
4. Org Chart Visualization
Auto-generated Mermaid diagram from agent configurations.
# Print Mermaid diagram
bun tools/OrgChart.ts
# Save as SVG (requires mmdc)
bun tools/OrgChart.ts --output svg --save org-chart.svg
5. Standing Orders (Heartbeat)
Recurring agent tasks executed on schedules — the PAI version of Paperclip's heartbeat engine.
# List all standing orders
bun tools/StandingOrders.ts list
# Enable/disable
bun tools/StandingOrders.ts enable daily-security-check
# Manually trigger
bun tools/StandingOrders.ts run friday-retro
# Sync to system cron
bun tools/StandingOrders.ts sync
Config: config/standing-orders.yml — agent schedules with goal links.
6. Config Export/Import
Portable, sanitized PAI configuration bundles for backup and sharing.
# Export (sanitized by default)
bun tools/ConfigExport.ts --output ~/exports/pai-config.tar.gz
# Import with dry run
bun tools/ConfigImport.ts pai-config.tar.gz --dry-run
# Import with merge (don't overwrite existing)
bun tools/ConfigImport.ts pai-config.tar.gz --merge
7. Multi-Workspace Isolation
Group agents, budgets, and goals by business domain.
Config: config/workspaces.yml — workspace definitions mapping agents to goals with budget pools.
8. Atomic Task Checkout
File-based locking prevents two agents from claiming the same task.
# Acquire lock
bun tools/TaskLock.ts acquire TASK-001 --agent hiram
# Release lock
bun tools/TaskLock.ts release TASK-001 --agent hiram
# Check status
bun tools/TaskLock.ts status TASK-001
# Clean stale locks (>30 min)
bun tools/TaskLock.ts cleanup --stale 30
Architecture
Governance/
├── SKILL.md # This file
├── tools/
│ ├── OrgChart.ts # Mermaid org chart generator
│ ├── BudgetReport.ts # Cost tracking and budget comparison
│ ├── GoalManager.ts # Goal hierarchy management
│ ├── ApprovalGate.ts # Telegram-based approval gates
│ ├── StandingOrders.ts # Heartbeat/recurring agent tasks
│ ├── ConfigExport.ts # Portable config export
│ ├── ConfigImport.ts # Config import with merge
│ └── TaskLock.ts # Atomic task checkout
├── config/
│ ├── budgets.yml # Per-agent spend limits
│ ├── approvals.yml # Approval gate definitions
│ ├── standing-orders.yml # Recurring agent schedules
│ └── workspaces.yml # Workspace isolation
└── reference/
└── PaperclipInspiration.md # Design decisions and Paperclip comparison
Design Principles
- CLI-first — Every feature is a TypeScript CLI tool (PAI Constitution Principle 8)
- File-based state — No database required; YAML configs and file locks
- Telegram-native governance — Approvals via existing Telegram bot infrastructure
- Goal-aware — Every agent action can trace back to a company objective
- Sanitize by default — Config exports strip secrets automatically
- Composable — Each tool works independently; combine via shell pipelines
Examples
Example 1: Morning governance check
User: "How are we doing on budgets this month?"
→ Runs BudgetReport.ts --budget
→ Shows per-agent spend vs limits
→ Flags any agents approaching thresholds
Example 2: Pre-deploy approval
User: "Deploy carbene.ai changes"
→ ApprovalGate.ts check deploy --agent hiram
→ Gate triggered → sends Telegram approval request
→ Waits for the user's "approve" reply
→ Proceeds with deployment
Example 3: Why are we doing this?
User: "What goal does the trading system serve?"
→ GoalManager.ts trace P7
→ "P7 (Joseph Trading System) → G3 (Generate investment returns via automated trading)"
→ Provides full context for decision-making
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: CarbeneAI
- Source: CarbeneAI/Forge
- License: MIT
- Homepage: http://carbene.ai/open-source
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.