A command that starts the Transmute software-building pipeline, either from beginning to end or at a selected stage. The pipeline organizes work such as requirements, implementation, audits, documentation, and deployment.

Use it to run the full pipeline, resume unfinished work, display help, or start a named stage such as implementation, security, accessibility, or performance.

It gives one entry point for running or resuming the project workflow instead of starting each stage manually.

cast — Command by VoxTechnologies

Install

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.

agentmods

npx agentmods add commands/voxtechnologies/transmute-framework/cast

Clone the repo

git clone --depth 1 https://github.com/VoxTechnologies/transmute-framework

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,171 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00011	$0.01171
Opus 5	$0.00005	$0.00585
Sonnet 5	$0.00002	$0.00234
Haiku 4.5	$0.00001	$0.00117

Measured 2d ago against content hash 40a36e462707, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cast 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.

commands/cast.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/transmute — Transmute Pipeline Controller

The user invoked /transmute $ARGUMENTS. Parse the argument $1 to determine the mode.

Mode Detection

Examine $1:

Empty, or full: Run the full pipeline via the transmute-pipeline agent
resume: Resume the pipeline from the last completed stage via the transmute-pipeline agent
help or ?: Display the help text below
Any other value: Match against the Stage Name Mapping table and invoke that stage's skill

Stage Name Mapping

Argument ($1)	Skill to Invoke	Stage
`tech-stack`	tech-stack	0
`brd`	brd	1
`prd`	prd	2
`validate` or `validate-specs`	validate-specs	2B
`scaffold`	scaffold	3
`implement`	implement	5
`audit-completeness` or `audit`	audit-completeness	5B
`security` or `audit-security`	audit-security	6A
`a11y` or `accessibility` or `audit-a11y`	audit-a11y	6B
`optimize` or `performance`	optimize	6C
`docs` or `documentation`	docs	6D
`refactor`	refactor	6E
`seed-data` or `seed`	seed-data	6F
`harden` or `resilience`	harden	6G
`prelaunch` or `pre-launch`	prelaunch	6H
`verify` or `verification`	verify	6V
`remediate` or `remediation`	remediate	6R
`polish`	polish	6P
`redesign` or `frontend-redesign` or `design-elevation`	redesign	6P-R
`smoke` or `smoke-test`	smoke	7V
`user-guide` or `guide`	user-guide	7D
`feedback`	feedback	8
`maintain` or `maintenance`	maintain	9

If $1 does not match any entry, show the help text and ask the user to try again.

Execution

Full Pipeline or Resume Mode

Spawn the transmute-pipeline agent using the Agent tool with the appropriate instruction:

Full mode: "Run the complete Transmute pipeline from Stage 0 through Stage 9. Read plancasting/_progress.md if it exists to skip already-completed stages."
Resume mode: "Resume the Transmute pipeline from the last completed stage. Read plancasting/_progress.md to determine current state."

Read the full file on GitHub · 102 lines

Changes

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 · 102 lines · 11 tokens per session scan A 40a36e462707

Subscribe to this mod's changes

cast is a command published in the GitHub repository VoxTechnologies/transmute-framework (4 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 1,171 once invoked, about $0.0001 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.

Code Generation DevOps and cloud Security Writing and docs ai-agent automation claude-code claude-code-plugin plan-casting

cast

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/transmute — Transmute Pipeline Controller

Mode Detection

Stage Name Mapping

Execution

Full Pipeline or Resume Mode

What this file has done since we first saw it

Other commands, from other repositories

install-context

doctor

status

webui

plan

plan