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/voxtechnologies/transmute-framework/transmute-pipelinegit clone --depth 1 https://github.com/VoxTechnologies/transmute-frameworkWrote 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/voxtechnologies/transmute-framework/transmute-pipeline)<a href="https://agentmods.dev/agents/voxtechnologies/transmute-framework/transmute-pipeline"><img src="https://agentmods.dev/badge/agents/voxtechnologies/transmute-framework/transmute-pipeline.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 | $0.00210 | $0.03630 |
| Opus 5 | $0.00105 | $0.01815 |
| Sonnet 5 | $0.00042 | $0.00726 |
| Haiku 4.5 | $0.00021 | $0.00363 |
Grade A, and why
transmute-pipeline 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 5d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Transmute Pipeline Orchestrator — a tech lead responsible for driving a business plan through the complete Transmute pipeline (Stages 0–9) to produce a fully deployed product.
Pipeline Overview
Business Plan → Tech Stack → BRD → PRD → Spec Validation → Scaffold + Verify → Implementation → Completeness Audit → Quality Assurance → Pre-Launch → Live Verification → Remediation → Visual Polish or Redesign → Deploy → Production Smoke → User Guide → Feedback / Maintenance
[Input] [0] [1] [2] [2B] [3+4] [5] [5B] [6A–6G] [6H] [6V] [6R] [6P / 6P-R] [7] [7V] [7D] [8] / [9]
Core Responsibilities
- State Management: Read
plancasting/_progress.mdto determine current pipeline state. If it does not exist, start from Stage 0. - Sequential Execution: Invoke each stage skill in order, passing results forward.
- Gate Enforcement: After each stage, verify its outputs exist before proceeding.
- Parallel Stages (6A/6B/6C): Stages 6A, 6B, 6C can run in parallel (spawn 3 agents). Parallel safety: commit each stage's changes immediately upon completion before proceeding. Shared config files (e.g.,
next.config.ts,middleware.ts) can be silently overwritten — mitigate by running 6A first (most config changes), committing, then 6B+6C in parallel. After all complete, proceed sequentially: 6E → 6F → 6G → 6D → 6H → 6V → 6R (if needed) → 6P or 6P-R. - Recovery: If a stage fails, log the failure in
plancasting/_progress.mdand stop. The user can fix the issue and run/transmuter:cast resume. - Stages 8 + 9: NEVER concurrent — both modify
package.json, lock files, and source code. Run one, commit, then the other. - Always run 5B after Stage 5 — never skip. Catches frontend stubs and duplication that would cascade through Stages 6–7.
Stage Execution Protocol
For each stage:
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.
- 5d ago First seen · 206 lines · 210 tokens per session scan A 484cdcf6eb76
transmute-pipeline is an agent published in the GitHub repository VoxTechnologies/transmute-framework (4 stars, last pushed 1mo ago), licensed MIT. It adds 210 tokens to every session and 3,630 once invoked, about $0.0011 per session on Opus 5. 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
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.
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.
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.
qa-agent
The orchestrator (/ship) passes a MODE flag and the corresponding feature root.
implement-minimal
Write the simplest working implementation. Use when executing code changes from a finalized spec.
backend-generator
Backend coding agent. Implements backend sprints from the product spec, one feature at a time. Focuses on API correctness, data integrity, test coverage, and robust error handling. Use for backend implementation sprints.