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 skills/voxtechnologies/transmute-framework/validate-specsnpx skills add VoxTechnologies/transmute-framework --skill validate-specsgit clone --depth 1 https://github.com/VoxTechnologies/transmute-frameworkWhat 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 | $0.00092 | $0.04399 |
| Opus 5 | $0.00046 | $0.02200 |
| Sonnet 5 | $0.00018 | $0.00880 |
| Haiku 4.5 | $0.00009 | $0.00440 |
Grade A, and why
validate-specs 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Transmute — Specification Validation (Stage 2B)
Read the detailed guide at ${CLAUDE_SKILL_ROOT}/references/validate-specs-detailed-guide.md for the complete validation procedures, teammate spawn prompts, and report templates.
Prerequisites
Before starting, verify:
./plancasting/brd/directory exists and contains markdown files. If missing, STOP: "Stage 2B requires completed BRD (Stage 1). Run Stage 1 first."./plancasting/prd/directory exists and contains markdown files. If missing, STOP: "Stage 2B requires completed PRD (Stage 2). Run Stage 2 first."./plancasting/tech-stack.mdexists. If missing, STOP: "Stage 2B requiresplancasting/tech-stack.mdfrom Stage 0. Run Stage 0 first."
Purpose
Independently cross-validate the BRD and PRD for consistency, completeness, and correctness — catching errors before they propagate into code. The BRD and PRD are generated by separate Agent Team sessions, so several categories of errors can slip through:
- BRD requirements overlooked or misinterpreted during PRD generation
- PRD specifications that contradict BRD constraints
- Terminology inconsistencies between documents
- Missing user stories for functional requirements
- Screen specs that don't match user flow descriptions
- API specs that don't cover all screen data needs
- Untestable acceptance criteria
- Cross-feature interactions documented in BRD but missing from PRD
Fixing these now costs minutes. Fixing them after code is written costs hours.
Inputs
Read:
- All files in
./plancasting/brd/, including_context.md - All files in
./plancasting/prd/, including_context.mdand_brd-issues.md(if exists — contains BRD quality issues pre-identified during PRD generation; map classifications: BLOCKING → CRITICAL, CRITICAL-BUT-RECOVERABLE → HIGH, NON-BLOCKING → MEDIUM/LOW) - All files in
./plancasting/businessplan/ ./plancasting/tech-stack.mdfor technical feasibility checks./plancasting/brd/_review-log.mdand./plancasting/prd/_review-log.mdif they exist
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 251 lines · 92 tokens per session scan A 6eea5b44942f
validate-specs is a skill published in the GitHub repository VoxTechnologies/transmute-framework (4 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 4,399 once invoked, about $0.0005 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 skills, from other repositories
knowledge-base
Create and maintain a Markdown knowledge base that any AI agent can read, search, and update. Use when the user wants to start a knowledge base, add or update notes, organize docs/notes for an agent or LLM to consume, build an index of notes, or run a cleanup/maintenance pass on an existing MD knowledge base. Triggers…
code-review
Use when code has been written and needs validation before committing, or when the user asks for a code review or security check.
test-generation
Use when the user asks for tests, mentions TDD, or when new code has been written and needs test coverage.
scientific-schematics
Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways…
statistical-power
Sample-size and statistical power calculations for planning studies. Use whenever someone asks "how many subjects/samples/replicates do I need", wants an a priori power analysis, a minimum detectable effect (MDE), a power curve, or needs to justify a sample size for a grant, IRB protocol, or pre-registration. Covers…
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…