invAIriant
AI-assisted architecture-audit skill + CLI for systems where invariants must survive change (Claude Code · Codex · Cursor)
Install with your AI
Paste into Claude Code, Cursor, or any agent — it reads the repo and wires the tool into your project.
Install and set up invAIriant (pip project) into my current project. Found on https://claudeers.com/invairiant Repo: https://github.com/mindicator/invAIriant Homepage/docs: — Detected install method: pip → pip install invairiant Category: skills. Platforms: cli. Read the repo's README for exact setup and env vars, then install it and wire it into my project. Claudeers Health Verdict: active; community-verified: false. Confirm the source before running anything.
pip install invairiant
git clone https://github.com/mindicator/invAIriant
// compatibility
| Platforms | cli |
|---|---|
| Operating systems | — |
| AI compatibility | claude |
| License | Apache-2.0 |
| Pricing | open-source |
| Language | Python |
invAIriant keeps architectural invariants from drifting under AI-assisted change.
Your coding agent runs the audit and gates the merge on real findings. Claude Code · Codex · Cursor.
No evidence. No finding.
![Real terminal recording: invairiant collect, then validate-report (OK), then ci-gate — FAILED, RFP-001 [S1], exit 1 blocking the merge](/_next/image?url=https%3A%2F%2Fraw.githubusercontent.com%2Fmindicator%2FinvAIriant%2FHEAD%2Fassets%2Finvairiant-demo.gif&w=1080&q=75)
An LLM can propose anything; only cited, verified findings count. invAIriant runs a named set of review lenses over a bounded change, then makes every candidate survive adversarial evidence checks before it becomes a finding. Lenses discover, evidence verifies, severity gates.
Status: early. Usable now as an agent skill; the CLI and CI support are intentionally small and deterministic.
Start
1. Add the skill to your agent — this is the audit:
mkdir -p .claude/skills && ln -s "$PWD/skill" .claude/skills/invairiant
# Codex / Cursor: see skill/README.md
2. Run it in the agent: /invairiant audit-pr → a paste-ready PR comment.
3. Gate CI (optional — the deterministic CLI seatbelt):
pip install invairiant
invairiant ci-gate report.json # exits 1 on an open S0/S1 finding
Worked examples
The low-latency-runtime example shows the core rule: a passing summary does not erase a verified finding. Five more worked audits in case-studies/, and a runnable demo in examples/refundpilot-demo/.
Learn more
- How it works — the pipeline and the evidence rules: docs/methodology.md
- The skill — every command and scope: skill/SKILL.md
- Lenses — 28 across 7 packs, pick 4–6 by risk: docs/lens-taxonomy.md
- The CLI: docs/cli.md · Gate PRs in CI: docs/github-action.md
- Walkthrough — a full run with real output: docs/demo.md
Not this
Not a linter, scanner, or proof of correctness; it turns their output into evidence and gates on verified findings. Not "AI, wander the repo and tell me what you think": it audits a bounded scope (a PR, a range, a module, an ADR) and refuses one it can't bound.
Apache-2.0 · © 2026 mindicator · Contributing · Roadmap
// faq
What is invAIriant?
AI-assisted architecture-audit skill + CLI for systems where invariants must survive change (Claude Code · Codex · Cursor). It is open-source on GitHub.
Is invAIriant free to use?
invAIriant is open-source under the Apache-2.0 license, so it is free to use.
What category does invAIriant belong to?
invAIriant is listed under skills in the Claudeers registry of Claude-compatible tools.
// embed badge
[](https://claudeers.com/invairiant)
// retro hit counter
[](https://claudeers.com/invairiant)
// reviews
// guestbook
// related in Claude Skills
🔓An agentic skills framework & software development methodology that works.
🔓
🔓💫 Toolkit to help you get started with Spec-Driven Development
🔓AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs,…