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/featuregit 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 | $0.01409 |
| Opus 5 | $0.00000 | $0.00705 |
| Sonnet 5 | $0.00000 | $0.00282 |
| Haiku 4.5 | $0.00000 | $0.00141 |
Grade A, and why
feature 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 2d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge:feature
Design, plan, and implement a new feature end-to-end with structured specs, parallel agent teams, and quality gates.
| Level | L1 Vibe Coder |
| Category | Feature Development |
| Syntax | /forge:feature [feature name or description] |
The Pipeline
graph LR
A["/forge:feature 'add auth'"] --> B["Phase A: Planner"]
B -->|approved spec| C["Phase B: Builder"]
B -->|approved spec| D["Phase B: Testing"]
C & D -->|code + tests| E["Phase C: Guardian"]
E -->|all gates pass| F[Done]
style C fill:#4a9,color:#fff
style D fill:#4a9,color:#fff
What It Does
/forge:feature is the full-lifecycle feature builder. It takes a feature idea from description through codebase analysis, spec generation, implementation, testing, and validation -- all in one command. The intelligence behind it is a three-phase agent pipeline: Phase A locks interface contracts via the planner agent, Phase B spawns builder and testing agents in parallel to write code and tests simultaneously, and Phase C runs a guardian agent quality gate to catch type errors, test failures, and security issues before you commit.
Before writing a single line, the command analyzes your existing codebase: directory structure, existing patterns, test conventions, and available dependencies. This means the generated spec accounts for how your project actually works, not how a generic project might work. The spec is saved to .claude/plans/ so you can review, modify, or revisit it later.
Without this command, planning a feature means mentally mapping the codebase, writing a spec document by hand, implementing sequentially (code first, tests after), and hoping you catch integration issues. /forge:feature parallelizes the build-and-test phase, enforces quality gates, and records the implementation as knowledge in the orchestrator for future reference.
Syntax & Options
/forge:feature [feature name or description]
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.
- 2d ago First seen · 129 lines · 0 tokens per session scan A 67f3345ba57a
feature 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 1,409 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.