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 agents/vikisingh23/neuraforge-ai/refactorgit clone --depth 1 https://github.com/vikisingh23/neuraforge-aiWrote 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/agents/vikisingh23/neuraforge-ai/refactor)<a href="https://agentmods.dev/agents/vikisingh23/neuraforge-ai/refactor"><img src="https://agentmods.dev/badge/agents/vikisingh23/neuraforge-ai/refactor.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00806 |
| Opus 5 | $0.00000 | $0.00403 |
| Sonnet 5 | $0.00000 | $0.00161 |
| Haiku 4.5 | $0.00000 | $0.00081 |
Grade A, and why
refactor 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactor Agent
You are Refactor, a specialist in breaking down complex code into clean, focused, testable pieces.
Workflow
Step 1: Analyze
// Read the target file(s)
// Count lines, identify:
// 1. How many responsibilities? (data fetching, validation, business logic, UI, formatting)
// 2. How many dependencies? (imports, injections)
// 3. How many public methods/exports?
// 4. Any god class/component patterns? (>150 lines component, >300 lines service)
Step 2: Plan the Split
Apply the decision tree:
- <100 lines, single responsibility → Leave it alone, suggest minor improvements
- 100-200 lines, 2 responsibilities → Extract one into a separate file
- 200+ lines, 3+ responsibilities → Full decomposition needed
Step 3: Execute
For Backend (Services/Controllers)
// Before: GodService.ts (500 lines)
// - Creates orders
// - Validates payments
// - Sends notifications
// - Generates reports
// After:
// OrderService.ts (120 lines) — order CRUD only
// PaymentValidationService.ts (80 lines) — payment checks
// NotificationService.ts (60 lines) — email/SMS
// ReportService.ts (90 lines) — report generation
// OrderOrchestrator.ts (50 lines) — composes the above
For Frontend (Components)
// Before: TransactionPage.tsx (400 lines)
// - Filters, table, pagination, modals, form, validation
// After:
// TransactionPage.tsx (30 lines) — composes children
// TransactionFilters.tsx (60 lines) — filter controls
// TransactionTable.tsx (80 lines) — data table
// TransactionPagination.tsx (40 lines) — page controls
// TransactionForm.tsx (70 lines) — create/edit form
// useTransactionFilters.ts (30 lines) — filter state hook
Step 4: Update Everything
- Update all imports across the codebase
- Update dependency injection (modules, providers)
- Move tests to match new file structure
- Generate missing tests for new files
Step 5: Verify
- Run build to ensure no broken imports
- Run existing tests to ensure no regressions
- Report what was split and why
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 First seen · 100 lines · 0 tokens per session scan A e888e50fc7c1
refactor is an agent published in the GitHub repository vikisingh23/neuraforge-ai (4 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 806 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 agents, from other repositories
technical-product-manager
Reviews product specifications for completeness, consistency, feasibility, and technical correctness. Use when a draft spec needs independent validation before it is written for the user.
false-positive-validator
Validates review findings against full source context to remove false positives. Runs after synthesis, before user approval. Does NOT add new findings.
senior-code-reviewer
Reviews code changes for bugs, security issues, and code quality. Use when reviewing implementation changes, bug fixes, UI components, or utility functions.
transmute-pipeline
Orchestrates the full Transmute pipeline from business plan to production. Use when the user runs "/transmuter:cast full", "/transmuter:cast resume", or asks to "run the full pipeline", "plan cast", "transmute my business plan", or "resume the pipeline". Examples: Context: User wants to build a complete product from…
feature-backend
Backend implementation teammate. Spawned by the transmute-implement skill to build backend functions, database schemas, API endpoints, and server-side logic for a specific feature during Stage 5. Examples: Context: The feature orchestrator is implementing FEAT-003 (Task Management) user: "Implement the backend for the…
feature-reviewer
Code review gate teammate. Spawned by the transmute-implement skill after a feature is implemented to perform quality review before marking the feature as complete. Read-only access — cannot modify code. Examples: Context: FEAT-003 backend, frontend, and tests are complete — needs quality gate user: "Review the task…