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 commands/nxtg-ai/forge-plugin/initgit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWhat 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 | $0.00000 | $0.01091 |
| Opus 5 | $0.00000 | $0.00545 |
| Sonnet 5 | $0.00000 | $0.00218 |
| Haiku 4.5 | $0.00000 | $0.00109 |
Grade A, and why
init 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge:init
Initialize NXTG-Forge governance in any project with a 60-second setup wizard that detects your stack and captures your vision.
| Level | L1 Vibe Coder |
| Category | Setup & Maintenance |
| Syntax | /forge:init |
What It Does
/forge:init is the starting point for every NXTG-Forge project. It runs a guided setup wizard that detects your project type (Node.js, Rust, Python, Go, Java), checks for existing configuration, captures your product vision and goals, then creates the governance files that power every other Forge command.
The wizard creates two files: .claude/governance.json (the project state tracker that records workstreams, quality gates, metrics, and sentinel audit entries) and optionally appends a Forge section to your CLAUDE.md with project context. This is all that is needed -- commands, agents, skills, and hooks are loaded automatically from the plugin.
Without /forge:init, you would need to manually create governance configuration, remember to track quality gates, and lose the contextual intelligence that makes commands like /forge:status and /forge:gap-analysis understand your project. The wizard replaces all of that with four questions and a confirmation.
Syntax & Options
/forge:init
This command takes no arguments. It runs interactively, asking questions via prompts.
When to Use It
- Starting a new project: Run it immediately after
git initand installing dependencies to establish governance from day one. - Onboarding an existing codebase: Point Forge at a mature project and let it detect the stack, then layer governance on top without disrupting existing workflows.
- After a fresh plugin install: The first command to run after
claude plugin install nxtg-forge.
Do not run /forge:init if .claude/governance.json already exists and is healthy. Use /forge:status instead to verify your current setup. If you need to reset, the wizard will detect existing config and offer a fresh-start option.
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 · 113 lines · 0 tokens per session scan A b01fc5bf0490
init is a command published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,091 tokens. 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 commands, from other repositories
paul:help
Show available PAUL commands and usage guide.
safe-refactor
Safe refactoring with automated review, testing, and rollback capabilities.
paul:verify
Guide manual user acceptance testing of recently built features.
expect
Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…
kill-mutants
Analyze surviving mutants from a mutation testing run and write targeted unit tests to kill them. Re-runs mutations to confirm kills.
mutate
Run mutation testing to verify test quality. Builds a custom mutation tool or uses an existing framework, runs mutations, and reports the mutation score with surviving mutants.