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 instructions/carbeneai/forge/claude-mdgit 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/instructions/carbeneai/forge/claude-md)<a href="https://agentmods.dev/instructions/carbeneai/forge/claude-md"><img src="https://agentmods.dev/badge/instructions/carbeneai/forge/claude-md.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 | $0.01720 | $0.01720 |
| Opus 5 | $0.00860 | $0.00860 |
| Sonnet 5 | $0.00344 | $0.00344 |
| Haiku 4.5 | $0.00172 | $0.00172 |
Grade A, and why
Forge CLAUDE.md 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 yesterday.
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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code when working in this repository.
Repository Overview
Forge by CarbeneAI is an open-source AI operations platform built on Claude Code. It provides skills-based architecture, specialized agent personalities, event-driven automation, and automatic work capture.
Technology Stack
| Component | Technology | Notes |
|---|---|---|
| Runtime | Bun | NOT Node.js |
| Language | TypeScript | Primary language for hooks and tools |
| Package Manager | Bun | NOT npm/yarn/pnpm |
| Platform | Claude Code | All features built around Claude Code's hooks and skills system |
Directory Structure
~/Forge/
├── .claude/
│ ├── settings.json # Configuration (PAI_DIR, DA name, env vars)
│ ├── .env # API keys (never committed)
│ ├── hooks/ # Event-driven automation (TypeScript)
│ │ ├── initialize-session.ts
│ │ ├── capture-all-events.ts
│ │ ├── capture-tool-output.ts
│ │ ├── stop-hook.ts
│ │ └── lib/pai-paths.ts # Centralized path resolution
│ ├── skills/ # 120 domain-specific capabilities
│ │ ├── CORE/ # Identity, architecture, principles
│ │ ├── Fabric/ # 248 native AI patterns
│ │ ├── Research/ # Multi-source research workflows
│ │ ├── Private/ # Local Ollama privacy routing
│ │ ├── Observability/ # Real-time agent monitoring dashboard
│ │ └── [90+ more]/
│ ├── agents/ # Specialized agent configs
│ ├── history/ # Automatic work capture (gitignored)
│ └── tools/ # System utilities
├── scripts/
│ ├── setup-new-machine.sh # Initial setup
│ └── pai-aliases.sh # Shell aliases
├── docs/ # Guides and references
├── CLAUDE.md # This file
└── README.md
Common Commands
# Initial setup on new machine
bash ~/Forge/scripts/setup-new-machine.sh
# Verify configuration
forge-check
# Run health check
forge-test
# List all skills / agents
forge-skills
forge-agents
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.
- yesterday First seen · 210 lines · 1,720 tokens per session scan A b98b95ca4341
Forge CLAUDE.md is an instructions file published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 1,720 tokens to every session, about $0.0086 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 2026-09-03.
Other instructions, from other repositories
medusa CLAUDE.md
Claude Code instructions for Pantheon-Security/medusa, covering medusa - medusa security scanning, critical: release gate — do not skip, 4. security hardening tests (must show: all pass), critical: bash sandbox and project overview.
numasec AGENTS.md
AGENTS.md instructions for FrancescoStabile/numasec, covering numasec agent guide, operating rules, branches, product direction and product messaging direction.
opencti_mcp_server CLAUDE.md
Claude Code instructions for CooperCyberCoffee/opencti_mcp_server, covering cooper cyber coffee opencti mcp server, project overview, recent features (v0.4.2), previous features (v0.4.1 and earlier) and development standards.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.