Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/carbeneai/forge/governancenpx skills add CarbeneAI/Forge --skill governancegit clone --depth 1 https://github.com/CarbeneAI/ForgeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/carbeneai/forge/governance)<a href="https://agentmods.dev/skills/carbeneai/forge/governance"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/governance.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.01557 |
| Opus 5 | $0.00038 | $0.00779 |
| Sonnet 5 | $0.00015 | $0.00311 |
| Haiku 4.5 | $0.00008 | $0.00156 |
Grade A, and why
Governance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- config/approvals.yml 1.2 KB
- config/budgets.yml 1.6 KB
- config/standing-orders.yml 2.1 KB
- config/workspaces.yml 1.5 KB
- reference/PaperclipInspiration.md 2.6 KB
- tools/ApprovalGate.ts 10 KB runs code
- tools/BudgetReport.ts 9.7 KB runs code
- tools/ConfigExport.ts 8.4 KB runs code
- tools/ConfigImport.ts 6.9 KB runs code
- tools/GoalManager.ts 7.8 KB runs code
- tools/OrgChart.ts 16 KB runs code
- tools/StandingOrders.ts 6.6 KB runs code
- tools/TaskLock.ts 6.3 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 197 lines · 76 tokens per session scan A 8dfc8b269bbd
Governance is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 1,557 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
scanning-containers-with-trivy-in-cicd
This skill covers integrating Aqua Security's Trivy scanner into CI/CD pipelines for comprehensive container image vulnerability detection. It addresses scanning Docker images for OS package and application dependency CVEs, detecting misconfigurations in Dockerfiles, scanning filesystem and git repositories, and…
implementing-code-signing-for-artifacts
This skill covers implementing code signing for build artifacts to ensure integrity and authenticity throughout the software supply chain. It addresses signing binaries, packages, and containers using GPG, Sigstore, and platform-specific signing tools, establishing trust chains, and verifying signatures in deployment…
aod-orchestrate
Multi-feature orchestration skill that bridges /aod.blueprint output to parallel wave execution. Groups synced GitHub Issues by ICE priority tier (P0/P1/P2) into sequential waves, creates Task records, spawns batch sessions via the orchestrator API, monitors completion, and reports results. Supports --issues…
building-vulnerability-dashboard-with-defectdojo
Deploy DefectDojo as a centralized vulnerability management dashboard with scanner integrations, deduplication, metrics tracking, and Jira ticketing workflows.
code-execution-helper
Guide for using code execution capabilities to perform parallel batch processing, conditional filtering, and data aggregation. This skill should be used when agents need to analyze multiple files efficiently, validate large result sets, aggregate data from multiple sources, or reduce token consumption through…
root-cause-analyzer
Implements 5 Whys root cause analysis methodology for systematic debugging and problem resolution. Use this skill when you need to find root cause, run 5 whys analysis, analyze recurring problems, or perform systematic debugging. Guides developers through structured analysis, documents findings in institutional…