Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/VoxTechnologies/transmute-frameworknpx agentmods add skills/voxtechnologies/transmute-framework/redesignWrote 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/skills/voxtechnologies/transmute-framework/redesign)<a href="https://agentmods.dev/skills/voxtechnologies/transmute-framework/redesign"><img src="https://agentmods.dev/badge/skills/voxtechnologies/transmute-framework/redesign/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/voxtechnologies/transmute-framework/redesign"><img src="https://agentmods.dev/badge/skills/voxtechnologies/transmute-framework/redesign.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00099 | $0.03621 |
| Opus 5.5 | $0.00040 | $0.01448 |
| Sonnet 5.5 | $0.00020 | $0.00724 |
| Haiku 4.5 | $0.00010 | $0.00362 |
Grade A, and why
redesign 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 26d 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stage 6P-R: Frontend Design Elevation (Interactive Redesign)
Unlike the standard Stage 6P (visual polish — which fixes defects within an existing design system), this stage performs a FULL design elevation: collecting project context interactively, studying reference products, extracting Figma design tokens, making deliberate design decisions with the user, and implementing a cohesive visual overhaul.
Read the detailed guide at ${CLAUDE_SKILL_DIR}/references/redesign-detailed-guide.md for full phases, anti-slop patterns, component matrices, review procedures, and report templates.
When to Use This vs. Standard 6P
| Scenario | Use |
|---|---|
| App looks functional but needs contrast fixes, hover states, spacing consistency | Standard 6P (polish skill) |
| App looks like generic AI-generated SaaS and needs a distinctive visual identity | This skill (redesign) |
| Rebranding or major design direction change | This skill |
| First-time design system establishment | This skill |
| Post-launch design refresh based on user feedback | This skill |
Pipeline Position
Stage 6P-R occupies the same pipeline slot as 6P (after all Stage 6 quality passes, before Stage 7 deployment). It is an ALTERNATIVE to standard 6P, not an addition. Run one or the other, not both. If 6P has already been run and you want to switch to 6P-R, revert 6P changes first (git revert the 6P commit).
Mutual Exclusion with 6P: 6P and 6P-R are mutually exclusive. To switch from 6P to 6P-R: (1) commit all current work including 6P changes, (2) revert the 6P commit with git revert <6P-commit-hash>, (3) Start a new session and run 6P-R.
Stage Sequence: ... → 6V → [6R — only if 6V found 6V-A/B issues] → 6P-R → 7 (Deploy) → 7V → 7D → 8 / 9
Prerequisites
-
Application must be fully built and functional. Stage 5 complete, Stage 5B audit passed. This stage changes ONLY visual presentation — never functional behavior.
-
Stage 6V/6R should be complete (if applicable):
- If 6R report exists: must show PASS or CONDITIONAL PASS
- If only 6V report exists: must show PASS or CONDITIONAL PASS with only 6V-C issues (6R correctly skipped — 6R cannot fix human-judgment issues)
- If 6V shows CONDITIONAL PASS with 6V-A/6V-B issues: STOP — run 6R first
- If neither exists: verify with operator that prior stages were intentionally skipped
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.
- 26d ago Changed · +2 lines 741f75c1bdff
- 1mo ago First seen · 239 lines · 99 tokens per session scan A 06643d921c84
redesign is a skill published in the GitHub repository VoxTechnologies/transmute-framework (5 stars, last pushed 15d ago), licensed MIT. It adds 99 tokens to every session and 3,621 once invoked, about $0.0004 per session on Opus 5.5. 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
design-restore
A set of rules for reproducing an administrative interface from reference screenshots with high visual accuracy.
restore
A workflow for rebuilding a working admin dashboard from reference screenshots and written specifications. It coordinates planning, code generation and checking for visual accuracy.
frontend-design
Frontend design standards and aesthetic guidelines. Provides grading criteria for visual design quality, originality, craft, and functionality. Referenced by the planner and frontend evaluator. Not directly user-invocable.
d2
D2 diagramming language reference for architecture diagrams, sequence diagrams, grid layouts, SQL tables, and class diagrams. Produces .d2 files rendered via CLI or playground.
planr-design
Run OpenPlanr design, design-loop, or design-review using portable board assets.
sxo
Search Experience Optimization (SXO), the bridge between SEO and UX/CRO. Audits the journey from the SERP click to the on-page goal: click-through factors (title, meta, rich results), then post-click signals that keep users and drive conversions: above-the-fold relevance and intent match, page speed / Core Web Vitals…