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 skills add VoxTechnologies/transmute-framework --skill refactorgit 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/skills/voxtechnologies/transmute-framework/refactor)<a href="https://agentmods.dev/skills/voxtechnologies/transmute-framework/refactor"><img src="https://agentmods.dev/badge/skills/voxtechnologies/transmute-framework/refactor/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/refactor"><img src="https://agentmods.dev/badge/skills/voxtechnologies/transmute-framework/refactor.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 | $0.00088 | $0.02761 |
| Opus 5.5 | $0.00035 | $0.01104 |
| Sonnet 5.5 | $0.00018 | $0.00552 |
| Haiku 4.5 | $0.00009 | $0.00276 |
Grade A, and why
refactor 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 24d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stage 6E: Code Quality and Architecture Refinement
Lead a multi-agent code refactoring project. Audit the COMPLETE codebase for code quality, eliminate duplication, improve abstractions, enforce consistency, and optimize architecture — without changing any external behavior.
Stage Sequence (recommended ordering): Stage 5B → 6A/6B/6C (parallel) → 6E (this stage) → 6F (Seed Data) → 6G (Resilience Hardening) → 6D (Documentation) → 6H (Pre-Launch) → 6V → 6R → 6P/6P-R → 7 (Deploy)
Cardinal Rule
NO BEHAVIORAL CHANGES. Refactoring changes internal structure without altering external behavior. Every test that passed before refactoring must still pass after. If a refactoring would require changes to tests that validate external behavior (API contracts, acceptance criteria), the behavior is changing — stop and reconsider. Tests validating implementation details (private functions, internal state) may be restructured.
Scope clarification: 'No behavioral changes' means no changes to external APIs or user-facing behavior. Internal function signatures MAY change if all call sites are updated atomically in the same commit.
Context: Why This Stage Exists
The Feature Orchestrator builds features one at a time, with each cycle's teammates having limited awareness of other features' implementation details. This produces a working product, but leaves behind:
- Duplicated utility functions and patterns across feature domains
- Missed abstraction opportunities
- Inconsistent naming, patterns, or conventions across features
- Schema and index redundancies from incremental additions
- Overly coupled code where cross-feature integration was added reactively
- Dead code from iterative fixes during quality gate cycles
Prerequisites
Verify before starting:
./plancasting/_audits/implementation-completeness/report.mdexists with PASS or CONDITIONAL PASS. If missing or FAIL, STOP — Stage 5B must pass first.- Read
./CLAUDE.mdand./plancasting/tech-stack.mdfor project conventions. - Check that
./plancasting/_audits/security/report.md(6A),./plancasting/_audits/accessibility/report.md(6B), and./plancasting/_audits/performance/report.md(6C) exist. If any are missing, WARN and document in the report. - Incomplete features (5B Category C): Skip refactoring features marked as incomplete. However, DO refactor shared utilities/hooks that incomplete features use (since other complete features may also depend on them).
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.
- 24d ago Changed · +2 lines 7f5f59dd2cea
- 1mo ago First seen · 165 lines · 88 tokens per session scan A 97610a174707
refactor is a skill published in the GitHub repository VoxTechnologies/transmute-framework (5 stars, last pushed 13d ago), licensed MIT. It adds 88 tokens to every session and 2,761 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
review
Reviews code changes for concrete bugs with P0-P2 prioritized findings. Uses parallel architectural and implementation reviewers, then validates findings to remove false positives. Use when reviewing a caller-supplied diff, branch, staged changes, file set, or pull request, and use fix mode with caller-supplied…
summary
Creates a decision-focused Moss change summary for reviewers who care about the problem, outcomes, trade-offs, and platform implications more than code structure. Use for pull-request summaries, release notes, branch or diff overviews, implementation handoffs, and explanations of what changed and why it matters.…
red-blue-review
An optional adversarial review process for requirement analyses. One agent produces the analysis, while an independent reviewer checks its report, database definitions, alignment records, and requirements for missed issues.
evaluate
Evaluate existing code using the ganvil evaluation framework. Automatically determines if the project is frontend, backend, or fullstack and applies the appropriate evaluator with four-dimension scoring. Use to QA-check any existing project or codebase.
sdd-audit
Internal — Comprehensive quality audit of generated code. Automatically called by sdd-gen after consistency check passes. Configurable via sdd.config.json.
sdd-check
Internal — Verify that generated code is consistent with its approved SDD specification. Automatically called by sdd-gen. Can also be invoked manually to detect drift after manual code changes.