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 core-nxtg-forgegit 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/core-nxtg-forge)<a href="https://agentmods.dev/skills/nxtg-ai/forge-plugin/core-nxtg-forge"><img src="https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/core-nxtg-forge/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/core-nxtg-forge"><img src="https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/core-nxtg-forge.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 | $0.00161 | $0.03250 |
| Opus 5.5 | $0.00064 | $0.01300 |
| Sonnet 5.5 | $0.00032 | $0.00650 |
| Haiku 4.5 | $0.00016 | $0.00325 |
Grade A, and why
Core NXTG-Forge 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 4d 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.
NXTG-Forge — Platform Ground Truth
NXTG-Forge is a governance-native AI development system with three independent repos wired only through MCP (no shared code). This skill is the authoritative map; verify against source before asserting behavior, because earlier docs invented CLI that never shipped (see Gotchas).
| Repo | What it is | Integration |
|---|---|---|
forge-orchestrator |
Rust binary forge (CLI + stdio MCP server) |
orchestrator-mcp (Rust) |
forge-plugin |
Pure-markdown Claude Code plugin — commands, agents, skills, hooks + a Node MCP server | governance-mcp (Node) |
forge-ui |
Vite 7 + React 19 dashboard on :5050; sign-in required since v3.4.1 | runs from its own repo (npm run dev), not spawned by the plugin. /nxtg-forge:dashboard is a separate static HTML snapshot that needs no server |
The forge CLI (forge-orchestrator binary)
These are the ONLY real subcommands (source: forge-orchestrator/src/main.rs, src/cli/):
forge init [name] # Initialize .forge/, detect AI tools on PATH, write state.json
forge plan # Generate task plan from SPEC.md
forge status [--events]# Task board / project state (zero-context-friendly recovery view)
forge run # Execute planned tasks autonomously
forge start # Interactive/guided run
forge verify # Run verification gate
forge uat [finding] # Record/inspect UAT findings
forge sync # Sync state with disk (task files ↔ state.json)
forge mcp # Start the stdio MCP server (JSON-RPC 2.0). No subcommands.
forge dashboard # Launch the TUI (ratatui) dashboard
forge ship [--auto] [--dry-run] # Ship gate
forge config <key> [value] # Read/write config
forge uninstall [--force]
There is no forge checkpoint, forge restore, forge recovery, forge feature,
forge health, forge gap-analysis, forge quality, forge generate, or forge spec
binary subcommand. Those verbs exist only as /nxtg-forge:* slash commands (below).
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.
- 4d ago Changed 63d1442e27d5
- 12d ago Changed · +8 tokens per session 8588b2c37d2f
- 1mo ago First seen · 197 lines · 153 tokens per session scan A 9d0c187c0077
Core NXTG-Forge is a skill published in the GitHub repository nxtg-ai/forge-plugin (6 stars, last pushed 4d ago), licensed MIT. It adds 161 tokens to every session and 3,250 once invoked, about $0.0006 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
task-dependency-patterns
Task Management patterns with TaskCreate, TaskUpdate, TaskGet, TaskList tools. Decompose complex work into trackable tasks with dependency chains. Use when managing multi-step implementations, coordinating parallel work, or tracking completion status.
product-frameworks
Product management frameworks for business cases, market analysis, strategy, prioritization, OKRs/KPIs, personas, requirements, and user research. Use when building ROI projections, competitive analysis, RICE scoring, OKR trees, user personas, PRDs, or usability testing plans.
review-proposals
Triages pending improvement-proposal MCP items — presents each with its scope and evidence, collects an accept/reject/defer decision per proposal, and carries out the disposition: project-scoped acceptances get their exact YAML applied to .taskorchestrator/config.yaml and pushed per-root; global acceptances get a…
adopt-project-scope
Migrates an already-populated, unscoped Task Orchestrator database in place to the project-scoping convention — creates a project anchor root, re-parents existing work trees under it, and writes rootId back to config.yaml. Use when a user says: adopt project scope, migrate this database to project scoping, make this…
status-progression
Navigates role transitions for MCP work items using advanceitem. Shows current role, gate status, required notes, and the correct trigger to use. Use when a user says: advance this item, move to work, start this task, complete this item, what's the next status, why can't I advance, unblock this, cancel this item, or…
work-summary
Generates a project dashboard from MCP work items. Default is a lean, attention-first view: what's in flight, what's blocked, what to do next, what's queued. Use when the user says: project status, what's active, show me the dashboard, work summary, what should I work on, project health, what's blocked, where did I…