SkillAgentSearch skills...

AIGX

Open, MIT context format for AI coding agents: centralized .aigx/ rules + a per-file boundary index that targets the right rules, forbidden imports, and gotchas to each file. The only context format validated in a controlled benchmark. Tool-agnostic; nothing injected into your source.

Install / Use

npx skills add Lolner95/AIGX

Installs into whichever agent you are using.

About this skill
πŸ“¦

Other

Other agent config

Quality Score

89/100

Supported Platforms

Claude Code
Cursor
Zed

Our assessment of AIGX

AIGX scores 89/100 on our quality scale, 398th of 963 AI & Machine Learning skills we index (top 42%).

Its Other is 18 KB long, well organised into 23 sections with 13 code examples: a thorough specification that gives an agent plenty to work with.

It has 130 GitHub stars, a meaningful sign that others use it.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
9/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so AIGX is actively maintained.
  • Our last check on 2026-10-21 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit β€” read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-24. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk β€” read a skill before letting an agent act on it.

AIGX compared with similar skills

All 4 of these similar skills score higher than AIGX; compare them before choosing.

SkillScoreStarsUpdatedFormat
AIGX (this skill)by Lolner958913045d agoOther
claude-memby thedotmack100113.6ktodayCLAUDE.md
Understand-Anythingby Egonex-AI10091.0k11d agoCLAUDE.md
headroomby headroomlabs-ai10079.0ktodayCLAUDE.md
CowAgentby zhayujie10047.8ktodayCLAUDE.md

Frequently asked questions

How do I install AIGX?
Run npx skills add Lolner95/AIGX. The install tabs above show the steps for each supported agent.
Which AI agents does AIGX work with?
It is written for Claude Code, Cursor and Zed, as a Other file. Other agents that read the same format can often use it too.
Is AIGX safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is AIGX still maintained?
The repository was last updated about 2 months ago, so AIGX is actively maintained.
<p align="center"> <img src="assets/logo.svg" alt="AIGX β€” AI Genome Exchange" width="560" /> </p> <p align="center"> <strong>The open, benchmark-validated context format for AI coding agents.</strong><br/> A <code>.aigx/</code> genome describes how your repo works β€” rules, per-file boundaries, gotchas β€” so any AI agent inherits your conventions and behaves like a senior engineer who already knows the code. </p> <p align="center"> <a href="LICENSE"><img src="https://img.shields.io/badge/tools-MIT-22c55e.svg" alt="MIT"/></a> <a href="standard/LICENSE"><img src="https://img.shields.io/badge/spec-CC--BY--4.0-3b82f6.svg" alt="CC-BY-4.0"/></a> <a href="https://www.npmjs.com/package/@aigx/cli"><img src="https://img.shields.io/npm/v/@aigx/cli?label=npm%20%40aigx%2Fcli&color=22c55e" alt="npm @aigx/cli"/></a> <a href="https://pypi.org/project/aigx/"><img src="https://img.shields.io/pypi/v/aigx?label=PyPI&color=3b82f6" alt="PyPI"/></a> <a href="https://crates.io/crates/aigx"><img src="https://img.shields.io/crates/v/aigx?label=crates.io&color=f59e0b" alt="crates.io"/></a> <a href="standard/AIGX-1.1.md"><img src="https://img.shields.io/badge/spec-v1.1-8b5cf6.svg" alt="Spec v1.1"/></a> <a href="BENCHMARK.md"><img src="https://img.shields.io/badge/benchmark-n%3D60%20Β·%202%20models-f59e0b.svg" alt="Benchmark"/></a> </p> <p align="center"> <a href="#-quick-start">Quick start</a> Β· <a href="#-install-the-toolchain">Install</a> Β· <a href="#-the-proof">The proof</a> Β· <a href="#-using-aigx-with-your-stack">Use it with your stack</a> Β· <a href="standard/AIGX-1.1.md">Spec</a> Β· <a href="docs/aigx-in-60-seconds.md">60-second intro</a> </p>

AIGX (AI Genome Exchange) stores a codebase's AI-agent rules in a centralized .aigx/ directory with a per-file boundary index β€” and injects nothing into your source code. To our knowledge it is the only context format ever validated in a controlled benchmark, where it was the only format to rank first on both a weaker and a stronger model (Claude Haiku 4.5 and Sonnet 4.6, n=60) while surviving ~24 deliberate attempts to beat it.

Straight about the statistics (up front): at n=60 the top formats are a statistical tie on the composite mean β€” AIGX is not a blowout. Its defensible edge is being the most consistent across models, the most robust under challenge, the simplest to author, and the only option measured at all. Full scope, limitations & critique responses β†’

<sub>Spec v1.1 (CC-BY-4.0) Β· Tools MIT Β· Tool-agnostic Β· Published on npm Β· PyPI Β· crates.io Β· Last updated 2026-06-20</sub>


πŸš€ Quick start

One command scaffolds a genome and wires up your AI agent(s):

npm create aigx
# or: npx create-aigx   (same thing)

It's interactive β€” pick Cursor / Claude Code / Copilot / Windsurf / Aider / AGENTS.md, choose CI, done:

your-repo/
β”œβ”€β”€ .aigx/
β”‚   β”œβ”€β”€ protocol.aigx        ← the read protocol every agent loads first
β”‚   β”œβ”€β”€ product.aigx         ← product context + freshness clause
β”‚   β”œβ”€β”€ architecture.aigx    ← per-concern rules  (ARCH-* ids)
β”‚   β”œβ”€β”€ engineering.aigx     ← hard-correctness invariants (ENG-* ids)
β”‚   β”œβ”€β”€ files.aigx           ← β˜… the per-file boundary index β€” fill this in
β”‚   └── agent.aigx           ← self-maintenance rules for agents
β”œβ”€β”€ .cursor/rules/aigx.mdc Β· CLAUDE.md Β· AGENTS.md Β· .windsurfrules Β· .aider.conf.yml
└── .github/{copilot-instructions.md, workflows/aigx-validate.yml}

Your source code is untouched. Then fill in three things β€” files.aigx (the keystone), your rules in architecture.aigx, and product.aigx β€” and validate with aigx lint. The 60-second intro and authoring guide walk you through it; a complete real-world genome is in examples/sourcing-app/.


πŸ“¦ Install the toolchain

AIGX ships three independent reference implementations (Node, Python, Rust) β€” install from whatever registry you already live in. They're held in lock-step by a conformance suite.

| You want… | Install | Gives you | |---|---|---| | Scaffold a genome | npm create aigx | the interactive scaffolder (create-aigx) | | The CLI (Node) | npm i -g @aigx/cli | the aigx command (@aigx/cli) | | The CLI / validator (Python) | pip install aigx | aigx + aigx-lint (PyPI) | | The CLI / validator (Rust) | cargo install aigx | the aigx binary (crates.io) | | Editor support | VS Code Marketplace β†’ AIGX Language Support | highlighting, hover, diagnostics, go-to-def (editors/vscode) | | Libraries (Node) | npm i @aigx/parser @aigx/lint | programmatic parse + validate |

# zero-install runs, too:
npx @aigx/cli lint
npx @aigx/cli resolve src/features/auth/login.ts

Naming note: npm reserves the bare aigx name, so the npm CLI is @aigx/cli β€” but the installed command is aigx everywhere. On PyPI and crates.io the package is plain aigx.


πŸ”¬ The proof

We built a controlled benchmark: one real TypeScript codebase with planted traps (deep-import violations, dependency cycles, cross-tenant leaks, cache-ordering bugs, hallucination β€” 10 hard pitfalls), held constant, with only the context format varying and semantic parity machine-enforced (every format carries the identical rules). The subject is an autonomous agent that greps, edits, and runs tests. Scoring is deterministic and tamper-proof.

| Format | Sonnet 4.6 mean | pass@1 | hidden | Haiku 4.5 mean | pass@1 | hidden | |---|:---:|:---:|:---:|:---:|:---:|:---:| | 🧬 AIGX | 95.4 | 0.92 | 98.6% | 93.5 | 0.78 | 96.0% | | Markdown | 95.1 | 0.80 | 96.4% | 92.2 | 0.70 | 93.6% | | XML | 93.1 | 0.80 | 93.8% | 92.3 | 0.75 | 93.3% | | In-source headers | 94.6 | 0.80 | 96.1% | 92.4 | 0.67 | 90.2% |

AIGX ranks first on mean, pass@1, and hidden-test pass on both models β€” but the honest story is consistency, not margin. Markdown is great on Sonnet yet near-last on Haiku; XML is the rough reverse. AIGX is the only format first on both tiers β€” and it survived ~24 challenger variants across 6 research rounds, every one of which failed to beat it.

πŸ”¬ Full method, models, sample sizes, raw data, and the challenger log β†’ BENCHMARK.md Β· honest caveats β†’ docs/limitations.md


πŸ›  Using AIGX with your stack

1 Β· Scaffold (interactive)

npm create aigx           # pick your agent(s) + CI, then fill in files.aigx
npm create aigx -- --yes  # non-interactive: scaffold everything (great for CI)

2 Β· The aigx CLI

Same six commands whether you installed via npm, pip, or cargo:

aigx init                 # scaffold a .aigx/ genome (also interactive)
aigx lint                 # validate: required files, resolving checks, no stale paths, no dup ids
aigx resolve <path>       # bounded output β€” print one file's boundary (role Β· forbid Β· gotcha Β· checks)
aigx doctor               # environment + genome health check
aigx format [--check]     # parity-safe whitespace normalization
aigx check-conformance    # report your genome's conformance level (G1–G4 + recommended)
$ aigx resolve src/features/meetings/bookMeeting.ts
Applicable genome: .aigx
Role:   Book a meeting (validate slot + contact)
Forbid: NEVER import @/features/suppliers/internal/*   [CRIT]
Gotcha: get contact_email from the suppliers PUBLIC api, never the internal mapper
Checks: ARCH-no-deep-imports, DATA-integer-cents, TEST-failing-first

3 Β· Validate in CI

The genome can't silently rot β€” wire the validator into CI so a moved/renamed file fails the build:

# .github/workflows/aigx-validate.yml
- run: npx --yes @aigx/cli lint        # or: pipx run aigx --root .  Β·  or: cargo run -p aigx -- lint

4 Β· Editor support β€” .aigx highlights everywhere

| Editor | How | |---|---| | VS Code / Cursor / Windsurf | Install AIGX Language Support β€” highlighting, file icons, snippets, rule-id autocomplete, hover on rule ids, go-to-definition, inline diagnostics, format, and AIGX: Resolve current file's boundary | | GitHub | .aigx already renders (via .gitattributes); a Linguist PR kit is ready for first-class support | | Sublime Text Β· TextMate Β· Zed | Ready-made configs in editors/ β€” all from one canonical TextMate grammar (source.aigx) |

5 Β· Programmatic (build on AIGX)

npm i @aigx/parser @aigx/lint
import { parseGenome } from '@aigx/parser'
import { lint } from '@aigx/lint'

const model = parseGenome('.')          // β†’ canonical JSON data model (matches the spec's schema)
const { ok, errors } = lint('.')        // β†’ the same checks as the CLI / aigx-lint

Python (pip install aigx) exposes the validator as aigx-lint and as import aigx_lint. For MCP clients and codebase-memory agents, resolve a boundary as JSON before graph/search context β€” see JIT Context Hydration.

6 Β· Wire any agent

npm create aigx configures these for you; or copy one file from integrations/:

| Cursor | Claude Code | GitHub Copilot | Windsurf | Aider | Generic | |---|---|---|---|---|---| | .cursor/rules/aigx.mdc | CLAUDE.md | .github/copilot-instructions.md | .windsurfrules | .aider.conf.yml | AGENTS.md |

For a custom agent, paste the one-paragraph addendum from the spec Β§12.3.


🧬 How it works

flowchart TD
    A["Agent gets a task<br/>e.g. 'add a field to bookMeeting'"] --> B["Reads .aigx/protocol.aigx<br/>(the read order)"]
    B --> C["Reads the concern files<br/>the task touches"]
    B --> D["For EACH file it will edit,<br/>looks up its entry in<br/>.aigx/files.aigx"]
    D --> E["Gets the binding constraint<br/>at the edit site:<br/>forbid Β· gotcha Β· check-ids"]
    C --> F["Implements the change"]
    E --> F
    F --> G["Verifies every &lt;check&gt; id<br/>before declaring done"]
    style A fill:#1e293b,stroke:#475569,color:#e2e8f0
    style D fill:#7c2d12,stroke:#ea580c,color:#fed7aa
    style E fill:#7c2d12,stroke:#ea580c,color:#fed7aa
    style G fill:#14532d,stroke:#22c55e,color:#bbf7d0

The magic is per-file addressability. Agentic models read selectively β€” they grep, open the file they're editing, and rarely re-scan a whole rule doc. AIGX makes the binding constraint for that file retrievable in one lookup (files.aigx), instead of buried in prose β€” and keeps it out of your source. We tested all three placements (global prose, inline-in-source, addressed index); the addressed index won, inlining lost. (the principles β†’)

Anatomy of a genome

<!-- .aigx/architecture.aigx β€” rules with stable, citable ids -->
<aigx-architecture>
  <rule id="ARCH-no-deep-imports">Import features only through their public barrel. Deep imports are forbidden.</rule>
</aigx-architecture>

<!-- .aigx/files.aigx β€” THE KEYSTONE: the binding constraint per edited file -->
<aigx-files>
  <file path="src/features/auth/login.ts" domain="auth">
    <role>Handle login β€” validate credentials, issue a session</role>
    <forbid pri="CRIT">NEVER import @/features/billing/internal/*</forbid>
    <gotcha>token expiry is checked at read-time, not issue-time</gotcha>
    <check>ARCH-no-deep-imports ENG-tenant-scope</check>
  </file>
</aigx-files>

| Biology | AIGX | |---|---| | Genome β€” the code that builds & runs an organism | .aigx/ β€” the context that runs an agent in your codebase | | *

Truncated for display β€” read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars130
CategoryAI
Updated1mo ago
Forks25

Languages

Python

Trust signals

88/100

From repository metadata: license, adoption, age and documentation. Not a code audit β€” see the Safety scan above for what the skill file itself contains.

1 medium
AIGX β€” Other: Install & Safety Check | SkillAgent