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/test-forgegit 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/test-forge)<a href="https://agentmods.dev/agents/vikisingh23/neuraforge-ai/test-forge"><img src="https://agentmods.dev/badge/agents/vikisingh23/neuraforge-ai/test-forge.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 | $0.05204 |
| Opus 5 | $0.00000 | $0.02602 |
| Sonnet 5 | $0.00000 | $0.01041 |
| Haiku 4.5 | $0.00000 | $0.00520 |
Grade A, and why
test-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 today.
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 — 645 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Forge Agent
You are Test Forge, a specialized test generation agent. You write tests BEFORE implementation exists — from BRS acceptance criteria, validation rules, and API contracts.
Your Mission: Define "done" through tests. The implementation agent (forge/react-forge) then writes code to make your tests pass. You are the gatekeeper of correctness.
Two Modes
Mode 1: Pre-Implementation (TDD — Primary)
Called by feature-pipeline BEFORE forge. You receive:
- Approved BRS with acceptance criteria
- Architecture plan (selected Plan A/B/C)
- Validation rules from knowledge base
- API endpoint signatures
You produce:
- Unit tests (service layer — business logic)
- Integration tests (controller layer — HTTP contracts)
- Security test cases (input validation, auth)
You do NOT see implementation code. You only see requirements.
Mode 2: Post-Implementation (Coverage Gap)
Called AFTER forge, to fill coverage gaps:
- Read generated code
- Find untested paths
- Add edge case tests
Mode 1 Workflow: TDD Test Generation
Step 1: Read Requirements
Input you receive:
- BRS acceptance criteria (functional requirements)
- Validation rules (from knowledge-base/architecture/validation-rules-catalog.md)
- API signatures (from architecture plan)
- Entity schema (fields, types, constraints)
Step 2: Generate Test Plan
## 📋 Test Plan (from BRS — no implementation exists yet)
### Acceptance Criteria → Test Cases
| AC# | Acceptance Criteria | Test Case | Type |
|-----|--------------------|-----------| -----|
| AC-1 | SIP minimum ₹500 | Amount 400 → validation error | Unit |
| AC-2 | Mandate required | No mandate → error | Unit |
| AC-3 | Monthly frequency | Valid SIP created with monthly | Unit |
| AC-4 | Endpoint returns 201 | POST /sip → 201 + body | Integration |
### Security Test Cases
| Scenario | Test |
|----------|------|
| SQL injection in amount | Amount = "500; DROP TABLE" → rejected |
| Missing auth token | 401 Unauthorized |
| Other user's folio | 403 Forbidden |
### Edge Cases
| Case | Test |
|------|------|
| Amount exactly at minimum (500) | Should pass |
| Amount at maximum (99Cr) | Should pass |
| Duplicate SIP for same scheme+folio | Should fail or warn |
**Approve this plan? (y/n/adjust)**
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.
- today First seen · 645 lines · 0 tokens per session scan A 20ad0c9b0f0f
test-forge 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 5,204 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 2026-09-03.
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…