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 skills add nxtg-ai/forge-plugin --skill domain-knowledgegit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWrote 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/nxtg-ai/forge-plugin/domain-knowledge)<a href="https://agentmods.dev/skills/nxtg-ai/forge-plugin/domain-knowledge"><img src="https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/domain-knowledge/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nxtg-ai/forge-plugin/domain-knowledge"><img src="https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/domain-knowledge.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00099 | $0.01401 |
| Opus 5.5 | $0.00040 | $0.00560 |
| Sonnet 5.5 | $0.00020 | $0.00280 |
| Haiku 4.5 | $0.00010 | $0.00140 |
Grade A, and why
Domain Knowledge 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 1mo 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NXTG-Forge Domain Knowledge
What NXTG-Forge is
A self-deploying AI development infrastructure for Claude Code. Not just a code generator — an intelligent scaffolding + orchestration system that reads a project's specification, plans tasks, dispatches specialized agents, and tracks state across the development lifecycle.
Mission: "From specification to production in minutes, not days."
It bridges idea → implementation by: (1) turning a natural-language spec into a task plan, (2) orchestrating specialized agents, (3) persisting state for recovery, (4) surfacing quality gaps, (5) integrating natively with Claude Code.
Problem it solves: static templates don't adapt; ordinary scaffolds have no context memory, no orchestration, no state, and no quality signal. NXTG-Forge adds AI-native intelligence to all four.
The 3-repo workspace (real, not a monorepo)
forge-ui/ React 19 + Vite dashboard (:5050)
forge-orchestrator/ Rust CLI + MCP server — binary: `forge`
forge-plugin/ Claude Code plugin (commands/agents/skills/hooks) — this repo
Integration is MCP-only; there are no cross-repo code imports.
Core concepts (at a glance)
- Project Specification — natural-language build description.
forge plan --generatereadsSPEC.md(orPRD.md/REQUIREMENTS.md/README.md). - Agent Orchestration — work split across specialized roles (Lead
Architect, Backend Master, CLI Artisan, Platform Builder, Integration
Specialist, QA Sentinel), each backed by an
agent-*sibling skill. - State Management — persisted to
.forge/state.jsonwith an append-only audit log at.forge/events.jsonl. - Clean Architecture — Domain → Application → Infrastructure → Interface, dependencies pointing inward only.
- Drift / Gap Analysis — health + gap signals via MCP tools
(
forge_get_health,forge_check_drift,forge_get_governance_health). - MCP Integration — plugin registers governance-mcp (Node) + orchestrator-mcp (Rust); semgrep-mcp optional.
What ships with it
3 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.
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.
- 1mo ago First seen · 122 lines · 99 tokens per session scan A ebc121ccec14
Domain Knowledge is a skill published in the GitHub repository nxtg-ai/forge-plugin (6 stars, last pushed 4d ago), licensed MIT. It adds 99 tokens to every session and 1,401 once invoked, about $0.0004 per session on Opus 5.5. 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 skills, from other repositories
rag-retrieval
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, agentic RAG, multimodal RAG, query decomposition, reranking, or pgvector search.
error-analysis
Evals-first error analysis for LLM apps: clusters real Langfuse or JSONL traces into a human-confirmed failure taxonomy with counts, then recommends binary pass/fail evals for recurring named modes. Use to learn what to measure before writing evals. Not for CI failures.
dev
One-command dev loop boot. Spins up portless (named HTTPS subdomain), emulate (stateful API mocks), the project's dev server, and an agent-browser session, all keyed to the current git branch. Use when starting a feature branch, switching worktrees, or returning to a project after a break. Skips silently with install…
testing-llm
LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing AI features, validating LLM outputs, or building evaluation pipelines.
accessibility
Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, React Aria component patterns, cognitive inclusion, native HTML-first philosophy, and user preference honoring. Use when implementing screen reader support, keyboard navigation, ARIA patterns, focus traps, accessible component libraries…
manage-schemas
Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…