Franken Alignment — AI skill for Claude Code
Evidence-carrying control system for powerful AI agents, featuring epistemic MVCC, authority graphs, progressive ATP evidence, and decision-sensitive introspection in pure safe Rust.
How to install Franken Alignment
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Dicklesworthstone/franken_alignment and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Franken Alignment does
Evidence-carrying control system for powerful AI agents, featuring epistemic MVCC, authority graphs, progressive ATP evidence, and decision-sensitive introspection in pure safe Rust.
Alternatives in AI
- Geo SEO Claude — GEO-first SEO skill for Claude Code 3.6k ★
- Sentrux — Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improveme 2.9k ★
- Wax — Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple S 791 ★
README
franken_alignment
[](./LICENSE) [](https://doc.rust-lang.org/edition-guide/rust-2024/) [](./rust-toolchain.toml) [](https://github.com/rust-secure-code/safety-dance/) [](https://github.com/Dicklesworthstone) [](./COMPREHENSIVE_PLAN_FOR_THE_DESIGN_OF_FRANKENALIGNMENT.md)
**Evidence-carrying control for powerful, potentially untrusted agents. Pure Rust. Structured concurrency. Versioned judgment. Economical introspection.**
# What runs today, from a source checkout (see Installation & local verification):
git clone https://github.com/Dicklesworthstone/franken_alignment
cd franken_alignment
RCH_REQUIRE_REMOTE=1 rch exec -- cargo +nightly-2026-09-07 test --locked -p fa-reference
RCH_REQUIRE_REMOTE=1 rch exec --base HEAD --clean-overlay --no-overlay -- cargo +nightly-2026-09-07 run --locked -p xtask -- check
**A note on tense (read this first).** This README is written in the **present tense, as if the entire design in [`COMPREHENSIVE_PLAN_FOR_THE_DESIGN_OF_FRANKENALIGNMENT.md`](./COMPREHENSIVE_PLAN_FOR_THE_DESIGN_OF_FRANKENALIGNMENT.md) is fully realized**: the target state where every performance and safety gate is green and every subsystem is live. This is a deliberate choice. It lets the document describe the *finished* system so it gets **trued-up in place as
Related Skills
Document Specialist Skill
Claude Code Skill. AI-powered software documentation automation. Professional software documentation specialis
Doxa
ΔΟΞΑ: Rust multi-agent terminal for Claude, Codex, GLM and DeepSeek, with Jev/SubQ Snap model routing, indepen
Gemini Agent Skills
A comprehensive collection of expert AI Agent Skills for Google Gemini, featuring a powerful CLI to convert an
Mythic Agent Coder CLI
Mythic CLI is a powerful, terminal-based Vibe Coding AI Operating System. Featuring a dual-layer Vector RAG su
Empirica
Make AI agents and AI workflows measurably reliable. Epistemic measurement, Noetic RAG, Sentinel gating, and g
Clarity Gate
Epistemic quality verification for RAG systems
Related Agents
Context Quality Reviewer
Reads CLAUDE.md and .claude/rules/ for a project and evaluates quality via LLM-judgment: length, internal cont
Vestige Rust Reviewer
Reviews Vestige Rust changes against CODESTYLE.md, CLAUDE.md and the PRD — the seven hard architecture rules,
Research Sufficiency Reviewer
Reviews completed legal research before drafting. Checks whether each planned issue has sufficient primary sou