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/optimizegit 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 | $0.01432 |
| Opus 5 | $0.00000 | $0.00716 |
| Sonnet 5 | $0.00000 | $0.00286 |
| Haiku 4.5 | $0.00000 | $0.00143 |
Grade A, and why
optimize 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge:optimize
Analyze your codebase across seven dimensions -- large files, type safety, dead code, dependencies, duplication, console statements, and TODO debt -- then optionally apply safe fixes.
| Level | L1 Vibe Coder |
| Category | Quality & Testing |
| Syntax | `/forge:optimize [--scope performance |
What It Does
/forge:optimize is the codebase health scanner. It examines seven dimensions of code quality: large files that need refactoring (over 300 lines), type safety issues (as any and as unknown casts), dead code (exported symbols never imported elsewhere), dependency health (outdated, unused, and vulnerable packages), code duplication (repeated patterns across files), console statements in production code, and TODO/FIXME/HACK technical debt markers.
When the Task tool is available, the command spawns three parallel agents -- a detective for code quality, a performance agent for dependencies, and another detective for dead code -- cutting analysis time by roughly 3x compared to sequential scanning. The results are merged into a single optimization report with a 0-100 score and five prioritized recommendations.
The --fix flag enables safe automated fixes, but never without approval. It runs the full analysis first, presents a fix plan showing exactly which files will change and how, then waits for explicit confirmation before any Edit or Write operation. Safe auto-fixes include removing unused imports, replacing console.log with structured logger calls, and removing clearly dead code.
Syntax & Options
/forge:optimize [--scope performance|bundle|deps|code-quality|types] [--fix] [--report]
| Option | Description |
|---|---|
--scope <area> |
Focus analysis on one area: performance, bundle, deps, code-quality, or types |
--fix |
Run analysis, present fix plan, and apply safe optimizations after approval |
--report |
Generate and save the optimization report to a file |
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 · 142 lines · 0 tokens per session scan A d98dbdae7235
optimize 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 1,432 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.